© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11195
    Prev
    Next
    INDEX
    Explanations

    references to violent and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and criminal acts

    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
    ãĥ¯ãĥ³
    -0.63
    erenn
    -0.62
    retty
    -0.60
    eday
    -0.57
    irteen
    -0.56
    schild
    -0.56
     anecd
    -0.56
    mittedly
    -0.54
    achus
    -0.53
    undrum
    -0.53
    POSITIVE LOGITS
     thereto
    0.80
     thereof
    0.79
    ↵Âł
    0.78
    )?
    0.76
     doesnt
    0.74
     didnt
    0.74
     dont
    0.74
     them
    0.73
     theirs
    0.73
     hers
    0.72
    Activations Density 1.267%

    No Known Activations