© 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. 32181
    Prev
    Next
    INDEX
    Explanations

    names of media companies and related phrases

    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
    447
    +0.17
    0.8%
    267
    +0.12
    0.6%
    343
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.17
    0.08
    267
    +0.12
    0.09
    606
    +0.11
    0.08
    Negative Logits
    cific
    -0.77
    antly
    -0.74
    aunder
    -0.72
    rosse
    -0.72
    piration
    -0.71
    erva
    -0.70
    antry
    -0.70
    wikipedia
    -0.69
    itudinal
    -0.69
    ezvous
    -0.67
    POSITIVE LOGITS
    Universal
    1.26
    SN
    0.93
     News
    0.84
    WS
    0.81
     Sports
    0.79
    OH
    0.76
     Corporation
    0.75
     Studios
    0.75
     affiliate
    0.74
     Universal
    0.74
    Activations Density 5.359%

    No Known Activations