© 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 EvalsExportsAPI 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. 33533
    Prev
    Next
    INDEX
    Explanations

    information related to research studies and data analysis in various fields

    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
    +0.39
    2.0%
    393
    +0.13
    0.7%
    385
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.39
    0.21
    393
    +0.13
    0.27
    362
    +0.11
    0.16
    Negative Logits
    yout
    -0.71
    needed
    -0.70
    KK
    -0.68
    inventoryQuantity
    -0.67
    ãĤ¦ãĤ¹
    -0.64
    entimes
    -0.64
    ealous
    -0.64
    facing
    -0.63
    icably
    -0.63
     proble
    -0.62
    POSITIVE LOGITS
     1981
    0.69
     various
    0.69
     afar
    0.66
     Ranch
    0.65
     Quant
    0.64
     1977
    0.64
     1979
    0.64
     2007
    0.63
     Argentina
    0.63
     1982
    0.63
    Activations Density 10.859%

    No Known Activations