© 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. 4275
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
     Nero
    -0.75
     precon
    -0.67
     subcontract
    -0.67
     SAP
    -0.66
     NAS
    -0.65
     Rothschild
    -0.63
     Alexandria
    -0.63
     Pharaoh
    -0.62
     detachment
    -0.61
     CPR
    -0.61
    POSITIVE LOGITS
    ources
    1.45
    omew
    1.44
    atisf
    1.39
    atellite
    1.39
    ixty
    1.38
    olutions
    1.37
    essions
    1.37
    lightly
    1.31
    ouls
    1.31
    ometime
    1.29
    Activations Density 0.092%

    No Known Activations