© 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. 6953
    Prev
    Next
    INDEX
    Explanations

    phrases related to public policy and government 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
    140
    +0.09
    0.4%
    258
    +0.09
    0.4%
    625
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.10
    115
    +0.09
    0.06
    575
    +0.09
    0.07
    Negative Logits
    jad
    -0.78
    nen
    -0.76
    ynt
    -0.73
    nar
    -0.68
    USD
    -0.66
    gyn
    -0.66
    halla
    -0.66
    Ö¼
    -0.66
    è¦ļéĨĴ
    -0.65
    wered
    -0.64
    POSITIVE LOGITS
    sector
    0.72
    ilts
    0.67
    oppable
    0.65
    !--
    0.64
    urses
    0.62
    etary
    0.60
    agents
    0.60
    facing
    0.60
     opinion
    0.59
    payer
    0.58
    Activations Density 1.197%

    No Known Activations