© 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. 1-RES-JB
    11. 20136
    Prev
    Next
    INDEX
    Explanations

    instances of physical violence or force

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to physical acts of beating or striking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orrow
    -0.71
    sol
    -0.64
    Newsletter
    -0.64
    iscal
    -0.64
    alg
    -0.63
    export
    -0.63
    berra
    -0.63
    osion
    -0.62
    omal
    -0.61
    responsible
    -0.61
    POSITIVE LOGITS
     beating
    1.08
    beat
    0.98
     beat
    0.93
     beaten
    0.93
    Beat
    0.84
     beats
    0.84
     Beat
    0.80
    enance
    0.79
     Rouse
    0.77
     whipping
    0.77
    Activations Density 0.009%

    No Known Activations