© 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. 40030
    Prev
    Next
    INDEX
    Explanations

    technical instructions in a step-by-step format

    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
    393
    +0.15
    0.7%
    537
    +0.12
    0.5%
    716
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.26
    393
    +0.12
    0.22
    43
    +0.10
    0.10
    Negative Logits
    ioned
    -0.74
    uyomi
    -0.64
     rubbed
    -0.64
    ifiers
    -0.63
     cheered
    -0.62
    ļéĨĴ
    -0.60
     suppressed
    -0.60
     Mechdragon
    -0.60
    edIn
    -0.59
     dissenting
    -0.59
    POSITIVE LOGITS
    committee
    1.03
    elect
    0.94
    factor
    0.91
    step
    0.89
    series
    0.88
    death
    0.86
    meter
    0.86
    date
    0.85
    arms
    0.84
    design
    0.84
    Activations Density 7.598%

    No Known Activations