© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14459
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance or emphasis, possibly related to company presence and politics

    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
    361
    +0.14
    0.5%
    609
    +0.14
    0.5%
    534
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.14
    0.04
    408
    +0.14
    0.07
    455
    +0.13
    0.07
    Negative Logits
    assetsadobe
    -1.02
    ilings
    -0.98
    ĺħ
    -0.96
    des
    -0.94
    tnc
    -0.94
    oxide
    -0.93
    asty
    -0.92
    ashington
    -0.89
     srf
    -0.87
    lish
    -0.86
    POSITIVE LOGITS
     redeem
    1.29
     conceivable
    1.15
     available
    1.14
     avail
    1.14
    able
    1.13
    soever
    1.10
     ever
    1.08
    ABLE
    1.03
     remaining
    1.02
     whatsoever
    0.96
    Activations Density 1.288%

    No Known Activations