© 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. 2788
    Prev
    Next
    INDEX
    Explanations

    technical instructions or commands related to computer operations

    oai_token-act-pair · gpt-3.5-turbo

    technical instructions and descriptions related to software and user interfaces

    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
    ²¾
    -0.50
     canceled
    -0.50
     intends
    -0.48
     collided
    -0.47
     anticip
    -0.47
     finalized
    -0.47
     hopes
    -0.46
     unanimous
    -0.46
    é¾į
    -0.45
     serves
    -0.44
    POSITIVE LOGITS
    !.
    0.93
    _.
    0.93
    `.
    0.87
    !".
    0.85
     :-)
    0.83
    !:
    0.82
     ;)
    0.82
     '.
    0.81
     ðŁĻĤ
    0.80
    .:
    0.80
    Activations Density 0.867%

    No Known Activations