© 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. 7320
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Bear" typically referring to a sports team or a character

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Bear" and related terms

    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
    ADRA
    -0.85
    unal
    -0.84
    ournal
    -0.81
    anwhile
    -0.80
    arcer
    -0.78
    selves
    -0.78
    istry
    -0.76
    uries
    -0.73
     Seym
    -0.71
    ugu
    -0.71
    POSITIVE LOGITS
    bear
    1.03
     Bear
    0.99
    cats
    0.97
     Bears
    0.94
     Gry
    0.91
    cone
    0.91
     Traps
    0.90
    chet
    0.88
    beit
    0.84
     Trap
    0.84
    Activations Density 0.015%

    No Known Activations