© 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. 8-RES-JB
    11. 6531
    Prev
    Next
    INDEX
    Explanations

    statistical data including percentages and figures

    oai_token-act-pair · gpt-3.5-turbo

    percentages and statistical data related to various categories or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     =================================================================
    -0.68
    .:
    -0.64
    .}
    -0.64
    .?
    -0.62
     .)
    -0.62
    .--
    -0.61
    .]
    -0.59
    :'
    -0.59
     ONLY
    -0.54
    oster
    -0.53
    POSITIVE LOGITS
    onement
    0.60
    !,
    0.60
    addons
    0.59
     etc
    0.57
    bryce
    0.56
    *,
    0.55
     Afric
    0.54
    conduct
    0.53
    Mich
    0.53
    ?,
    0.53
    Activations Density 0.418%

    No Known Activations