© 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. 0-RES-JB
    11. 1082
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative measures and propositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eka
    -0.91
     duo
    -0.70
     nationality
    -0.70
    ppy
    -0.69
     merc
    -0.68
    gha
    -0.68
    wu
    -0.68
     summoned
    -0.67
    ryu
    -0.67
     caravan
    -0.67
    POSITIVE LOGITS
     Measure
    3.33
    Measure
    2.49
     Proposition
    1.83
     Measures
    1.55
    atters
    1.38
    alle
    1.14
    adjust
    1.09
     Incre
    1.06
    ertain
    0.97
     Matters
    0.94
    Activations Density 0.034%

    No Known Activations