© 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. 7-RES-JB
    11. 23366
    Prev
    Next
    INDEX
    Explanations

    references to physical actions or symbols related to fists

    oai_token-act-pair · gpt-3.5-turbo

    references to physical confrontations and violence, particularly involving fists

    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
     Comfort
    -0.82
     Indigo
    -0.80
    tis
    -0.76
    seq
    -0.75
    DIT
    -0.71
     Agency
    -0.71
    Trend
    -0.70
    paren
    -0.68
    Recomm
    -0.67
    acent
    -0.67
    POSITIVE LOGITS
    ful
    0.90
    fights
    0.87
     clenched
    0.84
     blunt
    0.84
     clen
    0.84
     wielded
    0.81
    ulas
    0.76
    forcer
    0.75
     wielding
    0.75
     fist
    0.75
    Activations Density 0.066%

    No Known Activations