© 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. 13068
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social 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
    393
    +0.34
    1.6%
    603
    +0.10
    0.5%
    376
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.34
    0.13
    393
    +0.10
    0.14
    0
    +0.10
    0.12
    Negative Logits
    !:
    -0.72
    :(
    -0.71
    !--
    -0.71
    elle
    -0.69
    poke
    -0.68
    ibble
    -0.67
    é¾įåĸļ士
    -0.67
    pee
    -0.66
    omi
    -0.66
    bending
    -0.65
    POSITIVE LOGITS
     vice
    0.80
     onwards
    0.79
     thence
    0.72
     assorted
    0.72
    rogens
    0.71
     possibly
    0.71
     hence
    0.70
    ERSON
    0.68
     thus
    0.68
     others
    0.65
    Activations Density 1.909%

    No Known Activations