© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    names or terms related to historical figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names and cultural references

    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
    fml
    -0.77
    holders
    -0.68
    userc
    -0.68
    drivers
    -0.68
    apeshifter
    -0.68
    ept
    -0.67
    creen
    -0.66
    cheat
    -0.65
    people
    -0.65
    yout
    -0.65
    POSITIVE LOGITS
    sson
    1.50
     Berger
    1.26
     Garc
    1.17
     Romero
    1.16
     von
    1.15
     Sch
    1.10
     Ortiz
    1.10
     Jacobs
    1.07
     Herrera
    1.06
     Laur
    1.06
    Activations Density 0.261%

    No Known Activations