© 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. 9-RES-JB
    11. 6040
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Pe"

    oai_token-act-pair · gpt-3.5-turbo

    the character "Pe" or variations of it, likely related to people's names or specific references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    selves
    -0.82
    schild
    -0.72
    naire
    -0.71
     EDITION
    -0.71
    stretched
    -0.70
    etheless
    -0.68
    姫
    -0.65
    enance
    -0.65
     Balanced
    -0.65
     Misc
    -0.65
    POSITIVE LOGITS
    anut
    1.44
    anuts
    1.37
    asant
    1.21
    pperc
    1.13
    ppers
    1.12
    eking
    1.09
    gging
    1.08
    ggy
    1.07
    eper
    1.06
    oples
    1.06
    Activations Density 0.019%

    No Known Activations