© 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. 31530
    Prev
    Next
    INDEX
    Explanations

    commands and functions used in programming, specifically related to manipulating data and functions

    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
    +0.30
    1.5%
    561
    +0.13
    0.6%
    244
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.30
    0.28
    31
    +0.13
    0.13
    176
    +0.10
    0.07
    Negative Logits
     fundament
    -0.70
     cultivation
    -0.69
     Skinner
    -0.60
     Alpine
    -0.60
     Alps
    -0.59
     PSU
    -0.58
    accompan
    -0.58
     Adidas
    -0.56
     FIFA
    -0.56
     CPR
    -0.55
    POSITIVE LOGITS
     +=
    0.93
    ":[{"
    0.92
     :=
    0.87
    Output
    0.82
    Result
    0.79
    ":["
    0.78
    ++;
    0.77
     </
    0.74
    yr
    0.72
     Output
    0.69
    Activations Density 13.086%

    No Known Activations