© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13168
    Prev
    Next
    INDEX
    Explanations

    phrases related to action and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    conversational discourse markers and expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '>
    -0.90
    ãĢij
    -0.83
    ©¶æ
    -0.75
    ¶
    -0.75
    ËĪ
    -0.73
     ].
    -0.73
    >.
    -0.72
    %:
    -0.70
    etheless
    -0.66
    SCP
    -0.65
    POSITIVE LOGITS
    ,"
    2.43
    ),"
    2.19
    .,"
    2.19
    ,''
    2.01
    ,'"
    1.97
    ',"
    1.95
     ,"
    1.90
    "),
    1.79
    ",
    1.66
    )",
    1.60
    Activations Density 0.970%

    No Known Activations