© 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. 9-RES-JB
    11. 20751
    Prev
    Next
    INDEX
    Explanations

    medically related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of words or phrases indicating intrigue, complexity, or significant emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .''
    -0.66
    ''.
    -0.64
    '."
    -0.62
    .''.
    -0.61
    $.
    -0.59
    %.
    -0.56
    .</
    -0.56
    .[
    -0.55
    ."
    -0.55
    .'
    -0.54
    POSITIVE LOGITS
    entious
    0.68
    osponsors
    0.66
    ingly
    0.64
    canon
    0.63
    aciously
    0.63
     concise
    0.63
    recated
    0.62
    omatic
    0.62
    hematically
    0.61
     conject
    0.61
    Activations Density 1.255%

    No Known Activations