© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    numeric patterns and information like grade levels and ages

    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
     Throne
    -0.69
     Canaver
    -0.65
    ichick
    -0.64
     Warranty
    -0.64
     Taxi
    -0.63
    thy
    -0.62
    lyak
    -0.60
     monarchy
    -0.60
    ablishment
    -0.60
    sth
    -0.59
    POSITIVE LOGITS
     school
    1.53
     kindergarten
    1.53
     students
    1.48
    Students
    1.47
    school
    1.47
    School
    1.43
     classmates
    1.39
     kids
    1.34
     Students
    1.34
     School
    1.33
    Activations Density 0.598%

    No Known Activations