© 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. 34894
    Prev
    Next
    INDEX
    Explanations

    words related to the season of winter

    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
    575
    +0.13
    0.7%
    554
    +0.11
    0.6%
    447
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    571
    +0.13
    0.08
    27
    +0.11
    0.06
    649
    +0.11
    0.02
    Negative Logits
    ifice
    -0.72
    ocratic
    -0.69
    leon
    -0.68
    ocrat
    -0.67
    aurus
    -0.67
    anooga
    -0.66
    aur
    -0.66
    rative
    -0.65
    angler
    -0.64
    ronics
    -0.63
    POSITIVE LOGITS
    thur
    0.98
     Wonderland
    0.84
    fell
    0.72
     evenings
    0.70
     sol
    0.70
     Wolves
    0.70
     coats
    0.69
    hawks
    0.68
     mornings
    0.68
     Nights
    0.66
    Activations Density 6.689%

    No Known Activations