© 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. 35570
    Prev
    Next
    INDEX
    Explanations

    descriptions of various algorithms

    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
    +0.21
    1.0%
    288
    +0.17
    0.8%
    715
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    635
    +0.21
    0.07
    227
    +0.17
    0.04
    213
    +0.12
    0.06
    Negative Logits
    lihood
    -0.74
    shirt
    -0.71
    joy
    -0.69
    holders
    -0.67
    hold
    -0.67
    birth
    -0.67
    holder
    -0.65
    gets
    -0.63
     Banner
    -0.63
     quarters
    -0.63
    POSITIVE LOGITS
     algorithms
    1.04
     algorithm
    0.95
    ically
    0.94
    gorithm
    0.85
     optimization
    0.76
    agically
    0.75
    matically
    0.72
    gorith
    0.72
    atically
    0.69
    urally
    0.68
    Activations Density 7.453%

    No Known Activations