© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23838
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    questions or discussions about societal issues and their implications

    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
    ©¶æ¥µ
    -0.76
    igi
    -0.75
    DERR
    -0.74
    APD
    -0.73
    iHUD
    -0.69
    inery
    -0.68
    ullivan
    -0.66
    abor
    -0.66
    },"
    -0.65
    20439
    -0.64
    POSITIVE LOGITS
    ?
    2.14
    ?:
    1.99
    ?)
    1.95
    ?).
    1.94
    ?),
    1.93
    ?"
    1.93
    ?'
    1.87
    ?",
    1.85
    )?
    1.79
    ?,
    1.78
    Activations Density 0.946%

    No Known Activations