© 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. 6-RES-JB
    11. 2755
    Prev
    Next
    INDEX
    Explanations

    mentions of the material "steel" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the steel industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sembly
    -0.82
    uate
    -0.79
    romeda
    -0.75
     Kard
    -0.73
     Niet
    -0.72
     DOE
    -0.70
    olulu
    -0.70
    etheless
    -0.67
     Lori
    -0.64
    itia
    -0.63
    POSITIVE LOGITS
    Series
    1.15
    works
    1.09
     wool
    1.04
    workers
    1.04
    worker
    0.93
    steel
    0.88
    anguage
    0.86
    fish
    0.85
    heart
    0.84
     beams
    0.83
    Activations Density 0.017%

    No Known Activations