© 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. 4-RES-JB
    11. 10267
    Prev
    Next
    INDEX
    Explanations

    words involving protective gear like armor

    oai_token-act-pair · gpt-3.5-turbo

    mentions of protective gear or equipment

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

    No Comments

    Negative Logits
    cause
    -0.74
     Vide
    -0.73
    vous
    -0.72
    demon
    -0.71
    liam
    -0.67
     Bee
    -0.67
     EVENT
    -0.66
     Lakes
    -0.66
    apest
    -0.65
    CN
    -0.64
    POSITIVE LOGITS
     piercing
    1.11
     armour
    1.01
    ments
    0.97
     armor
    0.94
     worn
    0.93
     clad
    0.92
     Piercing
    0.89
     defences
    0.89
     thickness
    0.83
     penetration
    0.82
    Activations Density 0.007%

    No Known Activations