© 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. 21211
    Prev
    Next
    INDEX
    Explanations

    phrases related to violence or abuse

    oai_token-act-pair · gpt-3.5-turbo

    negative expressions associated with sexual violence

    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
    Interstitial
    -0.63
     redes
    -0.62
     forecasting
    -0.60
     exting
    -0.59
    acca
    -0.58
    PDF
    -0.58
    alore
    -0.58
    £ı
    -0.57
    Initial
    -0.57
     transcript
    -0.57
    POSITIVE LOGITS
     somebody
    1.56
     anybody
    1.45
     someone
    1.44
     him
    1.44
     me
    1.37
    someone
    1.33
     anyone
    1.23
    him
    1.19
     us
    1.09
     Him
    1.06
    Activations Density 0.403%

    No Known Activations