© 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. 4269
    Prev
    Next
    INDEX
    Explanations

    instances where something is being highlighted or showcased

    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
    sis
    -0.98
    alty
    -0.97
    externalActionCode
    -0.77
    女
    -0.76
    atum
    -0.73
    iyah
    -0.71
    ãĥ¼ãĥ«
    -0.70
    bell
    -0.70
    hood
    -0.70
    ogen
    -0.68
    POSITIVE LOGITS
     prominently
    1.53
     collaborations
    0.81
     celebrities
    0.73
    leck
    0.73
     heavily
    0.73
     performers
    0.72
     artwork
    0.70
     personalities
    0.70
     plenty
    0.69
     multimedia
    0.69
    Activations Density 0.050%

    No Known Activations