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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16594
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a distinct comparison or exception

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tumble
    -0.57
    tailed
    -0.52
     hunted
    -0.52
    ":[{"
    -0.52
     tyr
    -0.50
    "},"
    -0.48
     toast
    -0.48
     reproduce
    -0.48
    OTT
    -0.47
    prus
    -0.47
    POSITIVE LOGITS
    heid
    1.24
    icularly
    0.99
    ments
    0.86
     from
    0.83
    ively
    0.83
    ensive
    0.82
    ranging
    0.80
    ional
    0.78
    orial
    0.77
    selves
    0.77
    Activations Density 0.030%

    No Known Activations