© 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. 8-RES-JB
    11. 23477
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a relationship or similarity between two entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pairs or groups of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fecture
    -0.83
    Trend
    -0.76
    utic
    -0.74
    slaught
    -0.73
    esis
    -0.71
    krit
    -0.70
    nect
    -0.70
    abwe
    -0.69
    ournal
    -0.69
    uel
    -0.67
    POSITIVE LOGITS
     sides
    1.26
     halves
    1.17
     sexes
    1.07
     genders
    0.87
     extremes
    0.80
    edged
    0.77
     sets
    0.77
     thirds
    0.74
     parties
    0.73
     coasts
    0.73
    Activations Density 0.061%

    No Known Activations