© 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. 4-RES-JB
    11. 1285
    Prev
    Next
    INDEX
    Explanations

    differences and variations between objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of varying or differing concepts and their implications

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

    No Comments

    Negative Logits
     Prohibition
    -0.73
    CTV
    -0.71
    ocalypse
    -0.67
    arton
    -0.67
    apo
    -0.60
    encia
    -0.60
     Merrill
    -0.59
    uala
    -0.58
     Maintenance
    -0.58
     Marriott
    -0.57
    POSITIVE LOGITS
     sexes
    0.96
    styles
    0.94
     differing
    0.89
     contrasting
    0.86
     styles
    0.86
     philosophies
    0.85
     perspectives
    0.84
     different
    0.84
     configurations
    0.83
     interpretations
    0.82
    Activations Density 0.312%

    No Known Activations