© 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. 365
    Prev
    Next
    INDEX
    Explanations

    names and places related to political conflicts and agreements

    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
    417
    +0.05
    0.5%
    16
    +0.04
    0.5%
    211
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.05
    0.01
    288
    +0.04
    0.01
    421
    +0.04
    0.01
    Negative Logits
    rils
    -0.31
    aminer
    -0.30
    opus
    -0.28
    ikarp
    -0.27
    ails
    -0.27
    ammy
    -0.26
    oths
    -0.26
    rums
    -0.26
     Shards
    -0.26
     shards
    -0.26
    POSITIVE LOGITS
    BIL
    0.38
    INGTON
    0.29
    BILITY
    0.29
    STAT
    0.28
    CLASSIFIED
    0.28
    BLE
    0.28
    DEN
    0.28
    CLOSE
    0.28
    gettable
    0.27
    ASS
    0.27
    Activations Density 0.029%

    No Known Activations