© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 10542
    Prev
    Next
    INDEX
    Explanations

    words related to production processes or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to production processes or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leans
    -0.83
    aiman
    -0.83
    uckle
    -0.71
    aque
    -0.69
    laus
    -0.69
    abies
    -0.68
    ttp
    -0.66
    olulu
    -0.65
    escription
    -0.63
    scribe
    -0.63
    POSITIVE LOGITS
     quotas
    0.81
    yards
    0.77
     processes
    0.76
     capacity
    0.75
     brewery
    0.74
     capacities
    0.73
     machinery
    0.70
     Kurdistan
    0.70
     output
    0.70
     schedules
    0.69
    Activations Density 0.061%

    No Known Activations