© 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. 32607
    Prev
    Next
    INDEX
    Explanations

    film-related terms and movie reviews

    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
    120
    +0.09
    0.6%
    276
    +0.08
    0.5%
    4
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.23
    326
    +0.08
    0.22
    442
    +0.08
    0.09
    Negative Logits
    verend
    -0.56
    hov
    -0.54
    cius
    -0.53
    abor
    -0.52
    eering
    -0.51
    arta
    -0.51
     Conscious
    -0.50
    hand
    -0.50
    blance
    -0.49
    imov
    -0.49
    POSITIVE LOGITS
    otten
    0.73
    culosis
    0.61
    Rated
    0.55
    apy
    0.54
    atoes
    0.50
    Rating
    0.49
     tabl
    0.47
    Score
    0.47
     Sacrament
    0.46
     Surprise
    0.45
    Activations Density 8.440%

    No Known Activations