© 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. 4237
    Prev
    Next
    INDEX
    Explanations

    nutritional information such as protein, calcium, iron content, and carbohydrate percentages in food items

    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
    utsche
    -0.56
    absolute
    -0.56
     Privacy
    -0.54
    gov
    -0.52
    iors
    -0.51
     HIP
    -0.51
     Finch
    -0.51
     Anxiety
    -0.51
    Privacy
    -0.50
    é¾įå¥ij士
    -0.49
    POSITIVE LOGITS
    achev
    0.82
    azo
    0.69
    assisted
    0.64
    reau
    0.63
     increments
    0.63
     guiActiveUnfocused
    0.61
    ĵĺ
    0.60
     ingred
    0.59
    wt
    0.57
    ombo
    0.56
    Activations Density 0.865%

    No Known Activations