© 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. 4-RES-JB
    11. 15243
    Prev
    Next
    INDEX
    Explanations

    statements expressing disagreement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disagreement

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

    No Comments

    Negative Logits
    amina
    -0.80
    GV
    -0.71
    Ãł
    -0.67
     Roads
    -0.65
    oufl
    -0.63
    mary
    -0.63
    maximum
    -0.63
    annis
    -0.62
    spring
    -0.62
     Roller
    -0.61
    POSITIVE LOGITS
     disagree
    0.85
    edIn
    0.83
     vehemently
    0.81
    llah
    0.78
    ingly
    0.77
    rences
    0.76
    ially
    0.75
    ively
    0.73
    lihood
    0.73
     unanimously
    0.72
    Activations Density 0.027%

    No Known Activations