© 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. 900
    Prev
    Next
    INDEX
    Explanations

    words related to technology and product features

    oai_token-act-pair · gpt-3.5-turbo
    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
    82
    +0.05
    0.4%
    308
    +0.05
    0.4%
    212
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.05
    0.03
    545
    +0.05
    0.03
    232
    +0.05
    0.03
    Negative Logits
    rament
    -0.47
     som
    -0.40
    ript
    -0.38
    throp
    -0.38
    ramid
    -0.37
    ulic
    -0.36
    ivan
    -0.36
    atra
    -0.36
    roma
    -0.35
    ahu
    -0.35
    POSITIVE LOGITS
    ¿½
    0.37
    catentry
    0.36
     Cors
    0.34
     Smile
    0.33
    lot
    0.33
    oved
    0.32
     Percentage
    0.32
     Loving
    0.32
     Grizz
    0.31
     Finder
    0.31
    Activations Density 0.094%

    No Known Activations