© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 39867
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming, specifically related to handling properties, methods, and classes in an object-oriented context

    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
    526
    +0.06
    0.6%
    48
    +0.05
    0.5%
    59
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.06
    0.17
    352
    +0.05
    0.16
    154
    +0.05
    0.17
    Negative Logits
     Bucks
    -0.32
     MacArthur
    -0.31
    oleon
    -0.30
     Frem
    -0.29
     Pav
    -0.29
    riad
    -0.29
     VIDEOS
    -0.28
     felon
    -0.28
     Normandy
    -0.27
     mathemat
    -0.27
    POSITIVE LOGITS
    ppers
    0.56
    pper
    0.49
    ppings
    0.46
    iths
    0.44
     wra
    0.42
    ith
    0.40
    ider
    0.39
    bling
    0.37
    ught
    0.36
     wrapper
    0.36
    Activations Density 10.293%

    No Known Activations