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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 24478
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Haw" at varying degrees of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Haw."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mirror
    -0.68
     wise
    -0.68
     understatement
    -0.63
     INF
    -0.61
     Mayhem
    -0.61
     Gemini
    -0.60
     hardened
    -0.60
     digits
    -0.59
     amplified
    -0.59
    代
    -0.59
    POSITIVE LOGITS
    keye
    1.87
    keyes
    1.52
    aii
    1.52
    orth
    1.39
    kes
    1.22
    ijah
    1.17
    ker
    1.17
    kward
    1.16
    kers
    1.11
    kinson
    1.10
    Activations Density 0.037%

    No Known Activations