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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 14775
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols often used in coding or data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cients
    -0.77
    bably
    -0.77
     dign
    -0.75
    ppelin
    -0.72
    olesc
    -0.69
    xual
    -0.69
     prelim
    -0.68
    ordinate
    -0.67
    esses
    -0.67
    verbs
    -0.63
    POSITIVE LOGITS
    catentry
    0.89
    Wide
    0.77
    _.
    0.75
    (-
    0.73
    ""
    0.72
    Creat
    0.71
    ÃĹ
    0.70
    -+
    0.68
    \"
    0.67
    naire
    0.66
    Activations Density 0.009%

    No Known Activations