© 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. 8-RES-JB
    11. 20387
    Prev
    Next
    INDEX
    Explanations

    websites and web page elements

    oai_token-act-pair · gpt-3.5-turbo

    references to pages, sheets, and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.81
     coerc
    -0.71
     themselves
    -0.71
    azeera
    -0.68
     detrim
    -0.67
    \\\\
    -0.67
    bage
    -0.65
    tsky
    -0.64
     neighb
    -0.64
    omething
    -0.63
    POSITIVE LOGITS
    optional
    0.69
     huh
    0.67
     accompanies
    0.66
     eh
    0.66
    pdf
    0.65
    lua
    0.64
    gif
    0.63
    opens
    0.62
     courtesy
    0.61
    comes
    0.60
    Activations Density 0.600%

    No Known Activations