© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2090
    Prev
    Next
    INDEX
    Explanations

    keywords related to political discussions or debates

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and entities, particularly in a political or financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romeda
    -0.65
     Originally
    -0.64
    atile
    -0.60
    aples
    -0.58
     Gibbs
    -0.54
    perature
    -0.53
    itars
    -0.52
    ccording
    -0.51
     Osw
    -0.51
    Ĭ±
    -0.51
    POSITIVE LOGITS
    `.
    0.83
    .</
    0.73
    !".
    0.70
    '.
    0.68
    ?".
    0.66
    "!
    0.65
    .''
    0.64
    .'
    0.63
    ''.
    0.63
    ULTS
    0.62
    Activations Density 1.717%

    No Known Activations