© 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. 3-RES-JB
    11. 17878
    Prev
    Next
    INDEX
    Explanations

    locations or people mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "photo" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sheet
    -0.73
    drawn
    -0.69
    acious
    -0.67
    ded
    -0.66
    breaking
    -0.63
    vertisement
    -0.63
     resemb
    -0.62
    rooms
    -0.62
    iments
    -0.62
    hip
    -0.61
    POSITIVE LOGITS
    zzi
    1.27
    amera
    0.96
    ÄŁ
    0.88
    ota
    0.88
    oga
    0.87
    veland
    0.86
    hene
    0.84
    zzo
    0.83
    GP
    0.83
    zed
    0.80
    Activations Density 0.010%

    No Known Activations