© 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. 8-RES-JB
    11. 4249
    Prev
    Next
    INDEX
    Explanations

    the question "How [adjective] is [subject]?" or similar

    oai_token-act-pair · gpt-3.5-turbo

    questions related to age, quantity, and frequency

    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
    iHUD
    -0.78
    hig
    -0.69
    hover
    -0.68
    Interstitial
    -0.67
    UGE
    -0.61
    $.
    -0.59
    FAULT
    -0.59
    Pir
    -0.58
    porter
    -0.57
    %);
    -0.57
    POSITIVE LOGITS
    ?
    1.58
    ?"
    1.46
    ?!
    1.43
    ?:
    1.40
    ?'
    1.39
    ?)
    1.38
    !?
    1.37
    ?!"
    1.34
    ?]
    1.34
    ...?
    1.32
    Activations Density 0.110%

    No Known Activations