© 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. 10-RES-JB
    11. 4947
    Prev
    Next
    INDEX
    Explanations

    words related to quantities and capacities

    oai_token-act-pair · gpt-3.5-turbo

    language related to production and capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasco
    -0.71
    cation
    -0.71
    fml
    -0.70
    gey
    -0.69
    Truth
    -0.69
    sche
    -0.64
    士
    -0.63
    Gate
    -0.63
    hee
    -0.62
    jan
    -0.62
    POSITIVE LOGITS
     160
    1.37
     approximately
    1.35
     750
    1.33
     150
    1.32
     250
    1.32
     660
    1.31
     350
    1.30
     120
    1.30
     850
    1.30
     640
    1.30
    Activations Density 0.410%

    No Known Activations