© 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. 32355
    Prev
    Next
    INDEX
    Explanations

    texts related to computer programming and code snippets

    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
    +0.33
    1.7%
    481
    +0.21
    1.1%
    314
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.33
    0.25
    640
    +0.21
    0.27
    314
    +0.12
    -0.07
    Negative Logits
    wagen
    -0.69
     bureau
    -0.65
     millenn
    -0.65
     Dill
    -0.63
     laun
    -0.63
    ertodd
    -0.63
     sovere
    -0.61
     Telegram
    -0.60
     Sheriff
    -0.60
     semin
    -0.60
    POSITIVE LOGITS
    meta
    1.09
    empty
    0.94
    foo
    0.85
    true
    0.81
    apply
    0.81
    toc
    0.80
    pure
    0.80
    wow
    0.79
    define
    0.78
    make
    0.77
    Activations Density 13.547%

    No Known Activations