© 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. 7-RES-JB
    11. 21199
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and places of academic affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    universities and their locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¯
    -0.84
    yip
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.68
    rieg
    -0.68
    venge
    -0.65
    ynasty
    -0.64
     clauses
    -0.64
    ãĥ©
    -0.64
    é»Ĵ
    -0.62
    ãĤ©
    -0.62
    POSITIVE LOGITS
     Libraries
    1.02
     Extension
    1.00
     Faculty
    0.91
     Ethics
    0.91
     Teaching
    0.90
     School
    0.89
     Institute
    0.87
     Laboratory
    0.87
     Robotics
    0.86
     Cooperative
    0.83
    Activations Density 0.072%

    No Known Activations