© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 989
    Prev
    Next
    INDEX
    Explanations

    words related to biological terms, medical terms, and specific activities or actions

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "em" in words

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    176
    +0.14
    0.5%
    510
    +0.14
    0.4%
    592
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.14
    0.07
    639
    +0.14
    0.07
    701
    +0.14
    0.06
    Negative Logits
     Skydragon
    -1.21
    catentry
    -1.18
     taxp
    -1.10
    ADRA
    -1.08
    è£
    -1.08
     Flavoring
    -1.07
    hift
    -1.05
     Dragonbound
    -1.00
     Ll
    -1.00
    irie
    -0.99
    POSITIVE LOGITS
    icultural
    1.24
    rette
    1.03
    inite
    1.03
    phant
    1.02
    ardless
    1.02
    ulent
    1.01
    emonic
    0.99
    omorphic
    0.99
    mon
    0.99
     corpus
    0.98
    Activations Density 1.129%

    No Known Activations