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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40457
    Prev
    Next
    INDEX
    Explanations

    references to academic papers, research studies, and scientific journals

    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
    515
    +0.11
    0.5%
    583
    +0.10
    0.4%
    488
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.11
    0.07
    363
    +0.10
    0.07
    288
    +0.09
    0.14
    Negative Logits
     Franks
    -0.76
    ECH
    -0.73
    KK
    -0.68
     Fields
    -0.64
    Redd
    -0.63
     Cere
    -0.63
     Dreams
    -0.62
     Dys
    -0.61
    ICAN
    -0.61
     Pearce
    -0.61
    POSITIVE LOGITS
    uin
    0.97
    leys
    0.86
     vol
    0.83
    otaur
    0.78
    itatively
    0.78
    ifiable
    0.77
    kus
    0.77
    uble
    0.76
    lisher
    0.75
    mble
    0.74
    Activations Density 4.403%

    No Known Activations