© 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
    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. 35913
    Prev
    Next
    INDEX
    Explanations

    information related to box office performance, including opening numbers, rankings, sales, and revenue for films

    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
    +0.23
    1.1%
    17
    +0.09
    0.5%
    147
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.23
    0.07
    216
    +0.09
    0.08
    573
    +0.09
    0.05
    Negative Logits
     Mesh
    -0.63
    ndra
    -0.62
     Oss
    -0.60
    £ı
    -0.60
    pell
    -0.59
    imer
    -0.59
    onomous
    -0.58
     Peoples
    -0.58
     Fedora
    -0.57
     Blackwell
    -0.57
    POSITIVE LOGITS
     receipts
    0.81
    eers
    0.81
    utra
    0.73
    ovies
    0.69
    zers
    0.66
     revenues
    0.66
     gross
    0.64
     projections
    0.64
    culosis
    0.62
     multiplier
    0.62
    Activations Density 7.874%

    No Known Activations