© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 20340
    Prev
    Next
    INDEX
    Explanations

    mentions of the sports team "Bulls"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Chicago Bulls

    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
    SPONSORED
    -0.92
    igation
    -0.71
    nces
    -0.67
    OVA
    -0.65
    icular
    -0.64
    OPLE
    -0.64
    autical
    -0.64
    onymous
    -0.64
    forms
    -0.63
    onsense
    -0.63
    POSITIVE LOGITS
     Bulls
    1.14
    keyes
    0.86
    Zone
    0.73
    birds
    0.71
     Hots
    0.70
     Bears
    0.69
    mania
    0.67
     Tribune
    0.66
    ockets
    0.66
    hof
    0.66
    Activations Density 0.010%

    No Known Activations