© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    text related to moral and ethical judgments regarding societal issues

    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
    646
    +0.03
    0.4%
    156
    +0.03
    0.4%
    205
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.03
    0.02
    418
    +0.03
    0.02
    7
    +0.03
    0.01
    Negative Logits
    ython
    -0.21
    ledge
    -0.20
    ighters
    -0.20
    igning
    -0.19
    ighter
    -0.18
     aim
    -0.18
    arkin
    -0.18
    imentary
    -0.17
    oire
    -0.17
    REL
    -0.17
    POSITIVE LOGITS
    mobile
    0.22
     UNCLASSIFIED
    0.20
    %]
    0.20
     sd
    0.19
     trou
    0.18
    rha
    0.18
     chall
    0.18
    su
    0.17
     graft
    0.17
    Thumbnail
    0.17
    Activations Density 0.040%

    No Known Activations