© 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. 14294
    Prev
    Next
    INDEX
    Explanations

    code snippets related to software development

    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
    745
    +0.06
    0.6%
    459
    +0.05
    0.4%
    520
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.06
    0.09
    406
    +0.05
    0.11
    373
    +0.05
    -0.23
    Negative Logits
    lessness
    -0.40
     Gow
    -0.40
     Som
    -0.39
     Cind
    -0.38
     Dru
    -0.38
     Sut
    -0.37
     Beg
    -0.37
     Sark
    -0.37
     Cathy
    -0.36
     Foley
    -0.36
    POSITIVE LOGITS
    eco
    0.46
    omatic
    0.40
    ikuman
    0.40
    otype
    0.38
    azon
    0.38
    ultimate
    0.38
    adapt
    0.37
    ascript
    0.37
    ensis
    0.37
    agra
    0.37
    Activations Density 13.609%

    No Known Activations