© 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 EvalsExportsAPI 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. 3355
    Prev
    Next
    INDEX
    Explanations

    phrases related to general situations and actions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to the concepts of violence and societal issues

    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
     Particularly
    -0.78
    particularly
    -0.76
     sidx
    -0.75
     Specifically
    -0.75
     Especially
    -0.71
    arin
    -0.71
    significant
    -0.70
    ourage
    -0.68
    ierre
    -0.67
    especially
    -0.66
    POSITIVE LOGITS
     unaffected
    1.09
     unchanged
    1.08
     irrelevant
    1.06
     harmless
    1.03
     ignored
    1.02
     impunity
    0.99
     alright
    0.99
     unrem
    0.97
     shrugged
    0.96
     indifferent
    0.96
    Activations Density 0.576%

    No Known Activations