© 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. 4198
    Prev
    Next
    INDEX
    Explanations

    names with a title (like Mr. or Mrs.)

    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
    20439
    -0.76
     favour
    -0.64
     pione
    -0.64
     organising
    -0.62
    sbm
    -0.60
     actionGroup
    -0.60
     front
    -0.60
     fibre
    -0.59
     Stuff
    -0.54
     analyse
    -0.54
    POSITIVE LOGITS
    .,
    1.34
    .;
    1.23
    .?
    1.20
    .,"
    1.15
    ./
    1.14
    .-
    1.02
    .—
    0.99
    .),
    0.95
    .:
    0.94
    .--
    0.89
    Activations Density 0.137%

    No Known Activations