© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18804
    Prev
    Next
    INDEX
    Explanations

    specific items or products mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to items or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orks
    -0.74
     Winds
    -0.67
    sburgh
    -0.66
    nis
    -0.65
    ingen
    -0.64
     Harding
    -0.63
    FER
    -0.63
    eln
    -0.62
    sis
    -0.60
     Compton
    -0.59
    POSITIVE LOGITS
    ized
    1.09
    ize
    0.95
    ization
    0.92
    ious
    0.91
    ised
    0.90
    izer
    0.88
    istics
    0.87
    meal
    0.87
    izing
    0.82
    izers
    0.82
    Activations Density 0.035%

    No Known Activations