© 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 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. 6875
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'of'

    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
    393
    +0.31
    1.0%
    611
    +0.17
    0.6%
    669
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.31
    0.10
    611
    +0.17
    0.10
    97
    +0.16
    0.07
    Negative Logits
    PDF
    -0.94
     ridic
    -0.91
    agy
    -0.88
     preparations
    -0.88
    feat
    -0.86
     accur
    -0.85
    ertodd
    -0.84
     toile
    -0.81
     summar
    -0.81
     entit
    -0.81
    POSITIVE LOGITS
     course
    1.07
     whom
    1.05
     Concord
    0.96
    ortunately
    0.93
     Record
    0.92
     Offense
    0.91
     Nanto
    0.90
    lower
    0.87
    tnc
    0.86
     Pond
    0.86
    Activations Density 1.398%

    No Known Activations