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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6917
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent actions resulting in severe harm or death

    oai_token-act-pair · gpt-3.5-turbo

    phrases and actions related to violent or fatal events

    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
     Observer
    -0.66
     hospitality
    -0.60
     prosecutions
    -0.60
     Situation
    -0.58
     unaffected
    -0.58
     Anthem
    -0.58
     Trop
    -0.58
     outgoing
    -0.57
     Nasa
    -0.55
     GAM
    -0.55
    POSITIVE LOGITS
    wered
    0.98
    pless
    0.85
     pieces
    0.85
    ãĥİ
    0.83
    ffee
    0.83
     Pieces
    0.82
    ãĤ©
    0.81
     shred
    0.79
    othy
    0.76
     perfection
    0.76
    Activations Density 0.203%

    No Known Activations