© 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. 0-RES-JB
    11. 12180
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hathaway"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Hathaway" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipeg
    -0.73
     Cub
    -0.73
     Polish
    -0.70
    Cub
    -0.69
     pops
    -0.69
    packages
    -0.68
    iami
    -0.68
     PSP
    -0.68
     joints
    -0.67
    sy
    -0.67
    POSITIVE LOGITS
     Hath
    3.50
     Hilton
    1.75
    youtube
    1.70
     Amen
    1.28
     Shal
    1.10
     Hale
    1.07
     Levi
    1.07
     Rae
    1.00
    youtu
    0.98
     Ree
    0.97
    Activations Density 0.056%

    No Known Activations