© 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. 1-RES-JB
    11. 8680
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to class or social hierarchy, particularly concerning the bourgeoisie

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ceiling
    -0.73
     capsules
    -0.63
    idious
    -0.63
     eclipse
    -0.61
     itch
    -0.61
    ãĥ¼ãĥ³
    -0.60
    yson
    -0.60
     tiles
    -0.59
    Rated
    -0.59
     foil
    -0.59
    POSITIVE LOGITS
    bour
    1.59
    dain
    0.93
    yond
    0.91
    achelor
    0.84
    gian
    0.81
    hood
    0.80
    intosh
    0.79
     bour
    0.78
    ¿½
    0.77
     horizont
    0.76
    Activations Density 0.008%

    No Known Activations