© 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. 17179
    Prev
    Next
    INDEX
    Explanations

    instances where hands are raised or mentions of raising in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve raising physical objects or hands

    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
     Antar
    -0.73
    ucci
    -0.70
    Cola
    -0.67
    mys
    -0.65
    /
    -0.64
    umerable
    -0.63
    sson
    -0.63
    owski
    -0.62
    pps
    -0.62
    mate
    -0.62
    POSITIVE LOGITS
     eyebrows
    1.14
     eyebrow
    0.93
     ire
    0.85
     suspicions
    0.85
     awareness
    0.83
     Awareness
    0.78
     suspicion
    0.75
     objections
    0.74
    oft
    0.74
    aura
    0.73
    Activations Density 0.117%

    No Known Activations