© 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. 4-RES-JB
    11. 10930
    Prev
    Next
    INDEX
    Explanations

    the word "Card" followed by a number indicating a specific entity or person

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals associated with cards, specifically in the context of sports or legal matters

    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
    ¿½
    -0.98
    hower
    -0.82
    %]
    -0.73
    merce
    -0.70
    ithing
    -0.70
    ĸļ
    -0.70
    Ń·
    -0.69
     Siem
    -0.69
    akings
    -0.68
    ItemTracker
    -0.67
    POSITIVE LOGITS
    iovascular
    1.32
    ozo
    1.14
    inals
    1.07
    iac
    1.05
    iologist
    1.04
    board
    1.03
    assian
    1.02
    igans
    0.98
    igan
    0.97
    abul
    0.92
    Activations Density 0.016%

    No Known Activations