© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 2133
    Prev
    Next
    INDEX
    Explanations

    people's names and their affiliations or roles

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in a sports or entertainment context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pled
    -0.64
    />
    -0.63
    draft
    -0.61
    Conclusion
    -0.60
    ript
    -0.59
    #$
    -0.56
    notation
    -0.56
    .–
    -0.55
    relative
    -0.55
    olation
    -0.54
    POSITIVE LOGITS
     pictured
    0.88
    enegger
    0.81
    ashtra
    0.78
     enjoys
    0.75
     ventured
    0.74
     admits
    0.74
     debuted
    0.74
     tweeted
    0.73
     photographed
    0.72
     penned
    0.71
    Activations Density 0.324%

    No Known Activations