© 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. 2-RES-JB
    11. 18935
    Prev
    Next
    INDEX
    Explanations

    the presence of hints or suggestions in the text

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating implications or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bred
    -0.82
    bel
    -0.76
    ingham
    -0.75
    full
    -0.72
    FI
    -0.70
    lat
    -0.69
    abet
    -0.69
    boarding
    -0.68
    venge
    -0.68
    itar
    -0.68
    POSITIVE LOGITS
     hinted
    0.88
     Prelude
    0.73
     alluded
    0.73
    nesday
    0.71
     hints
    0.70
     depreciation
    0.69
    itial
    0.68
     omin
    0.68
     prominently
    0.67
     unanimously
    0.66
    Activations Density 0.018%

    No Known Activations