© 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. 20834
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a loss of control or limitations in a person's abilities or actions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to personal perceptions of competence and reality

    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
     unison
    -0.63
    their
    -0.63
     THEIR
    -0.62
    FTWARE
    -0.62
    aughtered
    -0.61
     samples
    -0.61
    selves
    -0.61
     respective
    -0.60
    uras
    -0.60
     husbands
    -0.58
    POSITIVE LOGITS
     himself
    1.42
     Himself
    1.15
     presiding
    1.00
    cipled
    0.97
     veto
    0.92
     reelection
    0.85
     his
    0.85
     lect
    0.84
     resign
    0.84
     unilaterally
    0.84
    Activations Density 0.557%

    No Known Activations