© 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. 1-RES-JB
    11. 24199
    Prev
    Next
    INDEX
    Explanations

    contractions where the words "do" and "not" are joined together

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases conveying refusal or resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancer
    -0.73
    Site
    -0.69
    cano
    -0.68
    Laun
    -0.63
    pages
    -0.62
     è£ıè
    -0.62
    itiz
    -0.62
    Pure
    -0.61
     Britann
    -0.60
    Intern
    -0.60
    POSITIVE LOGITS
     necessarily
    1.01
     bother
    0.97
    icably
    0.96
    urtles
    0.88
    icable
    0.85
    rieve
    0.85
     hesitate
    0.82
     exactly
    0.81
     seem
    0.77
     surpr
    0.75
    Activations Density 0.078%

    No Known Activations