© 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. 3-RES-JB
    11. 11342
    Prev
    Next
    INDEX
    Explanations

    references to clues or hints within text

    oai_token-act-pair · gpt-3.5-turbo

    references to clues or hints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kus
    -0.75
    rior
    -0.74
    lav
    -0.66
    rums
    -0.65
    die
    -0.64
    imposed
    -0.64
    rifice
    -0.63
    ofi
    -0.63
    requency
    -0.62
    nia
    -0.62
    POSITIVE LOGITS
     clue
    1.17
     hint
    1.06
     clues
    1.04
     hints
    0.85
     glean
    0.81
    TextColor
    0.78
    wcs
    0.77
     indicating
    0.70
     scrut
    0.69
     explan
    0.69
    Activations Density 0.012%

    No Known Activations