© 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. 16120
    Prev
    Next
    INDEX
    Explanations

    mentions or references to individuals named "Britney" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Brit," indicating a focus on British subjects or 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
     recess
    -0.79
    ATA
    -0.75
     caution
    -0.73
     chambers
    -0.69
    TPPStreamerBot
    -0.68
    ATING
    -0.66
    CVE
    -0.64
     assigning
    -0.63
     envelope
    -0.62
     Gemini
    -0.61
    POSITIVE LOGITS
    ney
    1.19
    ishers
    1.06
    tex
    0.96
    isher
    0.95
    neys
    0.95
    oise
    0.94
    icial
    0.94
    ophone
    0.93
    anni
    0.92
    pop
    0.92
    Activations Density 0.066%

    No Known Activations