© 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. 2-RES-JB
    11. 12824
    Prev
    Next
    INDEX
    Explanations

    punctuation marks within text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oiler
    -0.86
    owell
    -0.78
    owder
    -0.74
    redo
    -0.70
    erey
    -0.69
    aido
    -0.69
    oping
    -0.68
    onew
    -0.68
    mma
    -0.68
    gue
    -0.67
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.73
     personalities
    0.69
     behavi
    0.66
    sites
    0.66
    campus
    0.66
     respons
    0.63
     charact
    0.63
    Interstitial
    0.62
     commissions
    0.62
     collegiate
    0.62
    Activations Density 0.014%

    No Known Activations