© 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 EvalsExportsinterp-engineNEWAPI 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. 11431
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Horace" at various levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity associated with the term "Hor"

    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
    ãģ¦
    -0.74
    ãģ®éŃĶ
    -0.70
    anwhile
    -0.69
    0000000000000000
    -0.69
    eer
    -0.68
     Leilan
    -0.66
     vigorously
    -0.61
     admitting
    -0.61
    eers
    -0.60
     rated
    -0.60
    POSITIVE LOGITS
    izontal
    1.56
    izont
    1.47
    rible
    1.45
    izons
    1.31
    rors
    1.30
    ribly
    1.25
    izon
    1.22
    ror
    1.17
    cru
    1.10
    rified
    1.10
    Activations Density 0.042%

    No Known Activations