© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 33935
    Prev
    Next
    INDEX
    Explanations

    references to legal, political, and crime-related topics

    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
    481
    +0.25
    1.2%
    447
    +0.19
    0.9%
    80
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.25
    0.28
    67
    +0.19
    0.17
    308
    +0.11
    0.08
    Negative Logits
    EStream
    -0.76
    Ô
    -0.72
     bounded
    -0.71
     apr
    -0.70
    skirts
    -0.69
    kees
    -0.68
     dur
    -0.68
     neigh
    -0.67
     wand
    -0.66
     kne
    -0.65
    POSITIVE LOGITS
    CS
    0.85
    CI
    0.82
    EMS
    0.76
    EO
    0.73
    KA
    0.73
    HQ
    0.71
     Investigator
    0.71
     Division
    0.70
     Group
    0.70
    LD
    0.70
    Activations Density 12.885%

    No Known Activations