© 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. 14304
    Prev
    Next
    INDEX
    Explanations

    positive statements or instructions

    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
    640
    +0.20
    0.6%
    393
    +0.19
    0.6%
    718
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.20
    0.14
    718
    +0.19
    0.12
    104
    +0.16
    0.09
    Negative Logits
    hops
    -1.14
     pregnancies
    -1.00
    grain
    -0.98
     complexities
    -0.95
    heses
    -0.95
    andowski
    -0.95
    alore
    -0.94
     motivations
    -0.94
     intimidated
    -0.93
     loopholes
    -0.93
    POSITIVE LOGITS
    pload
    1.31
     commemorate
    1.30
     replace
    1.20
    ggles
    1.19
     eliminate
    1.16
     avoid
    1.15
     conserve
    1.15
     minimize
    1.13
     preserve
    1.12
     regain
    1.12
    Activations Density 1.485%

    No Known Activations