© 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. 8-RES-JB
    11. 3285
    Prev
    Next
    INDEX
    Explanations

    mentions of physical violence or attacks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of assault and aggressive behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.76
    ãĤ©
    -0.76
     snipp
    -0.72
    views
    -0.68
     Solitaire
    -0.68
    ocular
    -0.67
    overed
    -0.66
     CFR
    -0.66
    iku
    -0.65
    bard
    -0.64
    POSITIVE LOGITS
    iveness
    0.89
    ive
    0.85
    uous
    0.84
     assault
    0.84
     perpetrated
    0.82
    ively
    0.81
    quez
    0.79
     victim
    0.77
    ingly
    0.75
     leveled
    0.74
    Activations Density 0.034%

    No Known Activations