© 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. 32914
    Prev
    Next
    INDEX
    Explanations

    dates and time periods

    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
    447
    +0.15
    0.7%
    393
    +0.15
    0.7%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.22
    159
    +0.15
    0.08
    336
    +0.10
    0.05
    Negative Logits
     Izan
    -0.81
    76561
    -0.75
     Responsibility
    -0.73
    ilet
    -0.66
     viol
    -0.64
     Rated
    -0.62
     Genie
    -0.61
    Ctrl
    -0.61
    /#
    -0.61
     Controls
    -0.61
    POSITIVE LOGITS
     month
    1.12
     week
    1.10
     semester
    1.06
     year
    1.00
     afternoon
    0.98
     summer
    0.94
     evening
    0.92
     morning
    0.91
     decade
    0.88
     autumn
    0.85
    Activations Density 10.145%

    No Known Activations