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

    Neuronpedia

    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. 5976
    Prev
    Next
    INDEX
    Explanations

    passages related to historical and religious figures or events

    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
    175
    +0.15
    0.6%
    499
    +0.12
    0.5%
    749
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.15
    0.06
    175
    +0.12
    0.03
    690
    +0.10
    0.05
    Negative Logits
    effic
    -0.77
    claw
    -0.76
    efficiency
    -0.71
    factor
    -0.71
    arov
    -0.70
     ants
    -0.70
    owered
    -0.70
    hap
    -0.69
    pron
    -0.68
    omaly
    -0.67
    POSITIVE LOGITS
     excerpts
    1.22
     essays
    1.16
     narrated
    1.13
     anthology
    1.12
     published
    1.12
     poems
    1.05
     tapes
    1.05
     albums
    1.05
     memoir
    1.04
     titled
    1.04
    Activations Density 3.191%

    No Known Activations