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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20710
    Prev
    Next
    INDEX
    Explanations

    references to data or data analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to data and statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModLoader
    -1.04
    ovie
    -0.83
    aughs
    -0.71
    Interstitial
    -0.69
    vous
    -0.66
    creen
    -0.64
    inct
    -0.63
    aline
    -0.63
    WithNo
    -0.63
    ouston
    -0.62
    POSITIVE LOGITS
     collection
    1.04
     analytics
    1.02
     collected
    0.97
     visualization
    0.97
     disag
    0.91
     gathered
    0.88
     recorder
    0.87
    flow
    0.86
    collection
    0.85
    iologist
    0.84
    Activations Density 0.038%

    No Known Activations