© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36348
    Prev
    Next
    INDEX
    Explanations

    the number 'dozen'

    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
    +0.28
    1.4%
    497
    +0.11
    0.6%
    71
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.28
    0.25
    608
    +0.11
    0.19
    14
    +0.11
    0.07
    Negative Logits
    claimed
    -0.64
    hra
    -0.63
    estine
    -0.63
    bro
    -0.60
    thur
    -0.59
     mathemat
    -0.58
    asta
    -0.58
    î
    -0.57
    uria
    -0.57
    lands
    -0.57
    POSITIVE LOGITS
     thousand
    0.86
     dozen
    0.83
    acity
    0.83
     Thousand
    0.83
    uously
    0.82
    uous
    0.81
     consecutive
    0.75
     iterations
    0.74
     IMAGES
    0.73
    dozen
    0.72
    Activations Density 8.993%

    No Known Activations