© 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 EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 31703
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and organizations involved in political activities and terrorism

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    62
    +0.09
    0.6%
    223
    +0.08
    0.5%
    377
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.22
    479
    +0.08
    0.01
    423
    +0.07
    0.10
    Negative Logits
     enclosed
    -0.49
    abwe
    -0.48
     Kubrick
    -0.48
     Hitler
    -0.47
     flares
    -0.46
     flare
    -0.45
    İĭ
    -0.45
    ãĥķãĤ©
    -0.44
     attraction
    -0.44
     vit
    -0.43
    POSITIVE LOGITS
    akening
    0.69
    adesh
    0.69
    kward
    0.69
    ibaba
    0.66
    endi
    0.65
    cast
    0.63
    erd
    0.62
    rights
    0.58
    abit
    0.58
    LAN
    0.57
    Activations Density 9.634%

    No Known Activations