© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 14043
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to international relations and government

    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
    580
    +0.09
    0.5%
    683
    +0.09
    0.5%
    524
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.29
    580
    +0.09
    0.11
    160
    +0.08
    0.23
    Negative Logits
    yip
    -0.54
    agascar
    -0.51
     Horses
    -0.51
    ufact
    -0.51
    faced
    -0.49
    oppers
    -0.48
    illet
    -0.48
     âĶľ
    -0.47
    tein
    -0.47
    artney
    -0.47
    POSITIVE LOGITS
    Vector
    0.52
    ãĥĢ
    0.52
    Pacific
    0.51
    utor
    0.50
    tnc
    0.49
    adr
    0.49
    una
    0.48
    OPA
    0.46
     surrogate
    0.45
    oped
    0.45
    Activations Density 20.096%

    No Known Activations