© 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. 0-RES-JB
    11. 7871
    Prev
    Next
    INDEX
    Explanations

    keywords related to infographics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Inf" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dain
    -0.81
    rane
    -0.79
    mington
    -0.76
    ogue
    -0.75
    ë
    -0.75
     Whitman
    -0.72
    deen
    -0.71
    bard
    -0.70
    tackle
    -0.69
     rounding
    -0.69
    POSITIVE LOGITS
     Inf
    3.75
    Inf
    2.25
    inf
    1.83
     inf
    1.64
     INF
    1.51
     Ins
    1.25
     Imm
    1.17
     Immun
    1.12
     Infect
    1.08
     Inferno
    1.08
    Activations Density 0.008%

    No Known Activations