© 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 Local
    9. 6-RES_SCL-AJT
    11. 33641
    Prev
    Next
    INDEX
    Explanations

    information related to politics and policies

    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
    +0.15
    0.6%
    683
    +0.12
    0.5%
    316
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.15
    0.10
    316
    +0.12
    0.09
    360
    +0.12
    0.10
    Negative Logits
    rament
    -0.90
    izons
    -0.87
    kees
    -0.83
    ottage
    -0.82
    ocene
    -0.79
    anooga
    -0.79
    adena
    -0.78
    avez
    -0.78
    oes
    -0.77
    osit
    -0.75
    POSITIVE LOGITS
     conclud
    0.77
     repeats
    0.77
     revolving
    0.74
     Thomson
    0.73
    forth
    0.73
     reiterate
    0.72
     Transcript
    0.72
     echoing
    0.69
    nces
    0.68
     invoking
    0.68
    Activations Density 4.963%

    No Known Activations