© 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. 10-RES-JB
    11. 18847
    Prev
    Next
    INDEX
    Explanations

    political and judicial related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legislative actions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ;)
    -0.86
     :-)
    -0.84
    !).
    -0.80
    _.
    -0.76
    )).
    -0.76
     :)
    -0.75
    )."
    -0.75
    ++;
    -0.75
    )\
    -0.74
     anyway
    -0.73
    POSITIVE LOGITS
     regarding
    0.84
     concerning
    0.76
     surrounding
    0.73
     relating
    0.69
    oward
    0.68
     overseeing
    0.63
    ablishment
    0.61
    bestos
    0.61
     Regarding
    0.58
     pertaining
    0.58
    Activations Density 0.554%

    No Known Activations