© 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. 11-RES-JB
    11. 9876
    Prev
    Next
    INDEX
    Explanations

    information related to violent incidents or attacks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violent attacks and perpetrators

    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
    balance
    -0.73
    ffen
    -0.71
    gregation
    -0.67
    icter
    -0.67
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.65
     detrim
    -0.65
     epid
    -0.65
     childbirth
    -0.64
     Consent
    -0.64
    ixon
    -0.64
    POSITIVE LOGITS
     stormed
    1.34
     stole
    1.23
     detonated
    1.23
     attacked
    1.22
     infiltrated
    1.17
     disguised
    1.16
     hurled
    1.14
     hijacked
    1.14
     penetrated
    1.12
     blew
    1.11
    Activations Density 0.229%

    No Known Activations