© 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. 8-RES-JB
    11. 10196
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific concepts or attributes, often related to identity or characterization

    oai_token-act-pair · gpt-3.5-turbo

    specific medical and genetic terms or concepts related to health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĢĮ
    -0.61
    bably
    -0.58
    repre
    -0.56
    utenberg
    -0.56
    essage
    -0.56
     acknow
    -0.55
    CONCLUS
    -0.54
    NYSE
    -0.54
    upon
    -0.54
    Ô
    -0.54
    POSITIVE LOGITS
    ",
    1.72
    "
    1.71
    "?
    1.70
    "—
    1.68
    ".
    1.61
    "!
    1.60
    "-
    1.55
    ":
    1.55
    ")
    1.48
    "...
    1.46
    Activations Density 0.544%

    No Known Activations