© 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. 45911
    Prev
    Next
    INDEX
    Explanations

    references to the Jewish Sabbath and related traditions and practices

    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
    465
    +0.16
    0.7%
    7
    +0.16
    0.7%
    286
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.16
    0.14
    575
    +0.16
    0.15
    68
    +0.14
    0.08
    Negative Logits
    most
    -0.87
    piece
    -0.85
    lda
    -0.85
    govtrack
    -0.81
    stal
    -0.76
     Takeru
    -0.73
    ptives
    -0.73
    court
    -0.71
     Mongolia
    -0.71
    ted
    -0.71
    POSITIVE LOGITS
    ucket
    1.23
    itt
    1.15
    itte
    1.10
    its
    1.09
    arella
    1.08
    abis
    1.03
    alo
    1.00
    atar
    0.99
    abb
    0.96
    arre
    0.93
    Activations Density 5.585%

    No Known Activations