© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35085
    Prev
    Next
    INDEX
    Explanations

    unusual or peculiar occurrences and situations

    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
    609
    +0.11
    0.5%
    718
    +0.10
    0.5%
    642
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.04
    43
    +0.10
    0.06
    289
    +0.10
    -0.01
    Negative Logits
    Reviewed
    -0.73
    uberty
    -0.72
    zyk
    -0.71
    udder
    -0.70
    jri
    -0.69
    hend
    -0.68
    asers
    -0.67
    xual
    -0.66
    uden
    -0.66
    rarily
    -0.66
    POSITIVE LOGITS
    ball
    1.30
    ities
    1.16
    balls
    1.10
     numbered
    0.93
    ity
    0.91
    numbered
    0.88
    yssey
    0.85
    sm
    0.82
    est
    0.75
    ishly
    0.75
    Activations Density 5.642%

    No Known Activations