© 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. 6214
    Prev
    Next
    INDEX
    Explanations

    text related to options or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing slashes ("/")

    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
     Scrib
    -0.72
     achie
    -0.67
     exha
    -0.63
    Þ
    -0.62
     millionaires
    -0.62
     aspiration
    -0.61
     liner
    -0.61
     Herald
    -0.60
     Cats
    -0.59
     oun
    -0.59
    POSITIVE LOGITS
    or
    1.43
    possibly
    1.12
    OR
    1.10
    especially
    1.06
    probably
    0.97
    mostly
    0.94
    orians
    0.94
    usually
    0.93
    perhaps
    0.93
    etc
    0.92
    Activations Density 0.010%

    No Known Activations