© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14140
    Prev
    Next
    INDEX
    Explanations

    words related to volume control or measurement

    oai_token-act-pair · gpt-3.5-turbo

    references to 'volume' in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    artisan
    -0.85
    generic
    -0.77
    yg
    -0.74
    wart
    -0.74
    gotten
    -0.73
    athing
    -0.72
    unes
    -0.72
    roit
    -0.72
    lez
    -0.71
    enegger
    -0.71
    POSITIVE LOGITS
     discounts
    0.88
    umes
    0.87
     volumes
    0.84
    catentry
    0.83
     quantities
    0.75
     volume
    0.74
    iless
    0.73
     knob
    0.71
     plates
    0.68
    ONSORED
    0.67
    Activations Density 0.027%

    No Known Activations