© 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. 18944
    Prev
    Next
    INDEX
    Explanations

    specific mentions of figures in a research context

    oai_token-act-pair · gpt-3.5-turbo

    references to figures or graphs in a scientific context

    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
     ruining
    -0.65
    _>
    -0.61
     intel
    -0.60
     Reincarn
    -0.60
     Mechdragon
    -0.59
     mind
    -0.59
    soDeliveryDate
    -0.59
     NX
    -0.59
     immersion
    -0.58
     loving
    -0.57
    POSITIVE LOGITS
    Figure
    1.13
     largeDownload
    1.06
    FIG
    1.03
     illustrates
    1.02
     âĩ
    0.99
    Fig
    0.97
    Table
    0.95
    shows
    0.93
     Figure
    0.92
    figure
    0.91
    Activations Density 0.060%

    No Known Activations