© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 6950
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically related to rivers

    oai_token-act-pair · gpt-3.5-turbo

    prominent mentions of the Nile River and associated figures or terms

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

    No Comments

    Negative Logits
    dinand
    -0.74
    bara
    -0.70
    abella
    -0.69
    rawdownloadcloneembedreportprint
    -0.66
     Bullets
    -0.66
    verage
    -0.64
    onew
    -0.64
    IZE
    -0.63
    zai
    -0.63
    itud
    -0.62
    POSITIVE LOGITS
    lihood
    1.21
     Nile
    0.83
    opter
    0.77
    yards
    0.76
    alogy
    0.75
    oples
    0.73
    VID
    0.72
    uve
    0.70
    hyde
    0.70
    evil
    0.70
    Activations Density 0.049%

    No Known Activations