© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5549
    Prev
    Next
    INDEX
    Explanations

    references to being among the first to do something or be involved in a specific activity or event

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    608
    +0.10
    0.5%
    278
    +0.09
    0.5%
    727
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.10
    0.07
    5
    +0.09
    0.06
    422
    +0.09
    0.05
    Negative Logits
    terness
    -0.64
    ALD
    -0.63
    _.
    -0.61
    alities
    -0.60
    Operation
    -0.60
     Frey
    -0.59
    Comb
    -0.58
     Berks
    -0.57
    ancies
    -0.57
    escription
    -0.57
    POSITIVE LOGITS
    born
    0.76
     casualty
    0.69
    liest
    0.68
    govtrack
    0.65
     clam
    0.63
     forefront
    0.63
     favorite
    0.61
     arri
    0.60
     foremost
    0.59
     smartest
    0.58
    Activations Density 1.308%

    No Known Activations