© 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. 31684
    Prev
    Next
    INDEX
    Explanations

    HTML markup and code snippets with specific attributes or functions, like links, forms, or JavaScript methods

    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
    710
    +0.14
    0.6%
    289
    +0.14
    0.6%
    519
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.14
    0.06
    176
    +0.14
    0.03
    68
    +0.12
    0.03
    Negative Logits
     Rutherford
    -0.81
     whistle
    -0.79
    anchester
    -0.78
     weary
    -0.76
     Crow
    -0.76
     veter
    -0.75
     whist
    -0.74
     dram
    -0.71
     counting
    -0.71
     favour
    -0.70
    POSITIVE LOGITS
    âĸij
    0.99
    Insert
    0.98
     <!--
    0.97
    PIN
    0.94
    Appearance
    0.92
    âĸĴ
    0.91
    TPS
    0.89
    !--
    0.89
    icons
    0.87
    Page
    0.87
    Activations Density 3.209%

    No Known Activations