© 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. 7-RES-JB
    11. 24042
    Prev
    Next
    INDEX
    Explanations

    mention of terrorist activities or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endum
    -0.77
    galitarian
    -0.74
    dit
    -0.68
    bye
    -0.66
     Quartz
    -0.66
    resso
    -0.65
    flush
    -0.63
     Grape
    -0.63
    laus
    -0.62
    Salt
    -0.62
    POSITIVE LOGITS
    fully
    0.98
    abad
    0.95
     attacks
    0.88
     spree
    0.87
    efully
    0.86
    istan
    0.86
     raids
    0.83
    fulness
    0.82
    istani
    0.82
     bombing
    0.81
    Activations Density 0.011%

    No Known Activations