© 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. 40630
    Prev
    Next
    INDEX
    Explanations

    dates written in numeric 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
    447
    +0.12
    0.5%
    292
    +0.12
    0.5%
    497
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    607
    +0.12
    0.10
    384
    +0.12
    0.06
    525
    +0.11
    0.09
    Negative Logits
    Sing
    -0.85
    Offline
    -0.76
    ARI
    -0.74
     vain
    -0.72
    ased
    -0.70
     transact
    -0.69
     è£ıç
    -0.68
    uras
    -0.68
    ACTION
    -0.65
     redes
    -0.65
    POSITIVE LOGITS
     2025
    0.89
     maturity
    0.84
     2030
    0.84
     2050
    0.83
     GOODMAN
    0.83
     exhaustion
    0.79
     adulthood
    0.79
     onwards
    0.78
    acers
    0.76
    fifth
    0.76
    Activations Density 9.547%

    No Known Activations