© 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. 16814
    Prev
    Next
    INDEX
    Explanations

    keywords related to trending or popular stories

    oai_token-act-pair · gpt-3.5-turbo

    elements related to trending topics or stories

    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
    anguage
    -0.99
    utable
    -0.81
    aimon
    -0.77
    verett
    -0.75
    umenthal
    -0.74
    udder
    -0.74
    urations
    -0.73
    ptin
    -0.70
    istration
    -0.70
    ysc
    -0.70
    POSITIVE LOGITS
    Trend
    0.83
    fur
    0.83
     Trend
    0.75
     STOR
    0.74
    croft
    0.73
    Micro
    0.72
    åĬ
    0.71
    some
    0.71
    ebin
    0.70
    Sax
    0.67
    Activations Density 0.030%

    No Known Activations