© 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. 2-RES-JB
    11. 23241
    Prev
    Next
    INDEX
    Explanations

    names of software tools followed by numerical indicators

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and their associated terms in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¦
    -0.81
    occup
    -0.72
    ournal
    -0.71
    hov
    -0.70
    PER
    -0.69
    aminer
    -0.68
    ãģŁ
    -0.68
    onto
    -0.68
    WARD
    -0.68
    PRESS
    -0.67
    POSITIVE LOGITS
     Bald
    0.89
    reath
    0.77
     Dull
    0.72
     Nights
    0.71
    uci
    0.70
    ridges
    0.70
    folio
    0.70
    olor
    0.68
    umenthal
    0.68
    rawl
    0.68
    Activations Density 0.016%

    No Known Activations