© 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. 9-RES-JB
    11. 10403
    Prev
    Next
    INDEX
    Explanations

    IP addresses in the format of x.x.x.x

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical data and metadata related to dates and version numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.74
    iasco
    -0.73
    hemy
    -0.69
    ĵĺ
    -0.67
    manship
    -0.66
    acci
    -0.66
     ACTIONS
    -0.65
    omsky
    -0.65
    steen
    -0.64
    utical
    -0.64
    POSITIVE LOGITS
    ĸļ
    0.70
     Noon
    0.64
    atari
    0.62
    fal
    0.61
     wedge
    0.59
     alley
    0.57
    fee
    0.56
    xual
    0.55
     noon
    0.54
    mary
    0.54
    Activations Density 0.392%

    No Known Activations