© 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. 10-RES-JB
    11. 23416
    Prev
    Next
    INDEX
    Explanations

    terms related to the strength or intensity of a relationship or association between concepts or variables

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate degrees of relationship or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosis
    -0.89
    ulia
    -0.81
     Flavoring
    -0.76
    iatus
    -0.71
    monary
    -0.70
    ERAL
    -0.69
    abbage
    -0.68
    itivity
    -0.68
    ulton
    -0.67
    ortmund
    -0.67
    POSITIVE LOGITS
     involved
    1.12
     reliant
    1.09
     linked
    1.04
     implicated
    1.03
     excluded
    1.02
     affected
    1.01
     employed
    1.00
     associated
    0.99
     connected
    0.99
     aligned
    0.99
    Activations Density 0.157%

    No Known Activations