© 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
    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. 31683
    Prev
    Next
    INDEX
    Explanations

    statements of proof or demonstration

    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
    +0.19
    0.8%
    288
    +0.12
    0.5%
    748
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.19
    0.02
    375
    +0.12
    0.05
    544
    +0.12
    0.07
    Negative Logits
     newsletters
    -0.86
    letal
    -0.78
    ropri
    -0.72
     contrace
    -0.69
     Peninsula
    -0.68
    EStreamFrame
    -0.68
    ovo
    -0.67
    lished
    -0.66
     column
    -0.66
     Clinic
    -0.65
    POSITIVE LOGITS
    \\\\\\\\
    1.01
    reader
    0.95
    ãĤ¤ãĥĪ
    0.79
    nces
    0.79
    ¯¯
    0.77
    manship
    0.77
    ance
    0.76
    ||||
    0.75
    uable
    0.75
    stal
    0.75
    Activations Density 10.633%

    No Known Activations