© 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. 8-RES-JB
    11. 6047
    Prev
    Next
    INDEX
    Explanations

    actions involving physical work or tasks

    oai_token-act-pair · gpt-3.5-turbo

    actions related to physical activities and workmanship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vanquished
    -0.75
     defeated
    -0.73
    raltar
    -0.72
    è¦
    -0.70
    llah
    -0.68
    urated
    -0.67
    ressed
    -0.63
     settled
    -0.62
     vict
    -0.61
     Benef
    -0.61
    POSITIVE LOGITS
     chores
    0.98
     bidding
    0.92
     simulations
    0.89
     internship
    0.89
     rounds
    0.87
     homework
    0.86
     stint
    0.85
     conversions
    0.83
     reconnaissance
    0.83
     assignments
    0.78
    Activations Density 0.369%

    No Known Activations