© 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. 9-RES-JB
    11. 2252
    Prev
    Next
    INDEX
    Explanations

    phrases related to completion or resolution, often indicating clearing a path or getting something out of the way

    oai_token-act-pair · gpt-3.5-turbo
    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
    PsyNetMessage
    -0.69
    olicy
    -0.68
    utical
    -0.68
    ãĥį
    -0.66
    Continue
    -0.63
    bryce
    -0.63
    JUST
    -0.63
    owicz
    -0.62
    AIN
    -0.62
    illac
    -0.60
    POSITIVE LOGITS
     equation
    1.05
     gate
    0.94
     closet
    0.94
     frying
    0.88
     gates
    0.85
     jaws
    0.83
     loop
    0.83
     woods
    0.82
     mouths
    0.80
     drawer
    0.78
    Activations Density 0.092%

    No Known Activations