© 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. 11-RES-JB
    11. 18622
    Prev
    Next
    INDEX
    Explanations

    terms related to metadata and analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to meta-analysis and related statistical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.90
    shire
    -0.77
    wic
    -0.73
    nia
    -0.72
    stall
    -0.70
    icates
    -0.69
    ongs
    -0.64
    ishment
    -0.64
    uci
    -0.64
    sen
    -0.63
    POSITIVE LOGITS
    ethical
    1.11
    verse
    1.07
    HER
    1.01
    Mask
    0.97
    Crit
    0.96
    economic
    0.93
    plot
    0.92
    engineering
    0.92
    econom
    0.91
    JSON
    0.89
    Activations Density 0.078%

    No Known Activations