© 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. 34856
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or temporal comparisons

    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
    350
    +0.11
    0.4%
    616
    +0.10
    0.4%
    178
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.10
    162
    +0.10
    0.06
    175
    +0.10
    0.03
    Negative Logits
    mates
    -0.79
     McGee
    -0.79
    mate
    -0.76
    ohyd
    -0.75
    reditary
    -0.75
     salads
    -0.75
    uay
    -0.74
    ttes
    -0.74
     Leilan
    -0.73
    arthed
    -0.73
    POSITIVE LOGITS
     vein
    0.99
     level
    0.79
    rity
    0.77
     denomination
    0.72
    IFF
    0.72
     shaky
    0.71
     token
    0.70
     expense
    0.68
     exact
    0.68
     rate
    0.67
    Activations Density 3.882%

    No Known Activations