© 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. 6-RES-JB
    11. 17403
    Prev
    Next
    INDEX
    Explanations

    numerical values with three zeros

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly concerning quantities or statistics

    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
    venge
    -0.75
    sole
    -0.74
    ufact
    -0.73
     tremend
    -0.69
    nam
    -0.66
     Prelude
    -0.66
    abus
    -0.60
    rival
    -0.57
    sid
    -0.57
    gotten
    -0.56
    POSITIVE LOGITS
    bps
    0.92
    lb
    0.91
     lbs
    0.90
    lbs
    0.88
     pounds
    0.85
    mAh
    0.84
     acres
    0.84
     crore
    0.84
     hectares
    0.84
    ths
    0.83
    Activations Density 0.087%

    No Known Activations