© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19467
    Prev
    Next
    INDEX
    Explanations

    mentions of NCAA Division I sports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific divisions in competitive settings

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

    No Comments

    Negative Logits
    FORE
    -0.83
    uated
    -0.69
    packing
    -0.69
    chell
    -0.65
     unaccompanied
    -0.63
    wrap
    -0.63
    uter
    -0.62
    gotten
    -0.61
    uates
    -0.61
    astic
    -0.61
    POSITIVE LOGITS
    al
    0.95
    alis
    0.80
    ISION
    0.76
    ally
    0.73
    ality
    0.72
    naire
    0.72
     Mines
    0.71
     Division
    0.71
    alities
    0.69
    heses
    0.68
    Activations Density 0.009%

    No Known Activations