© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23857
    Prev
    Next
    INDEX
    Explanations

    mentions of large measurements, especially related to physical spaces like square feet or kilometers

    oai_token-act-pair · gpt-3.5-turbo

    measurements of area and volume, particularly in square feet and square miles

    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
    Lear
    -0.77
     Cron
    -0.63
     Cance
    -0.61
     Noon
    -0.61
    occ
    -0.59
    gotten
    -0.59
    bye
    -0.58
     ALS
    -0.58
    ror
    -0.57
     cyn
    -0.56
    POSITIVE LOGITS
    ynthesis
    0.83
    ²
    0.83
    essions
    0.74
     footprint
    0.73
     canvas
    0.71
    elsius
    0.71
     (~
    0.71
     acres
    0.70
     âĶľâĶĢâĶĢ
    0.69
    .;
    0.69
    Activations Density 0.067%

    No Known Activations