© 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. 0-RES-JB
    11. 16345
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hart" followed by a number indicating significance or action related to the mentioned name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Hart."

    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
    Android
    -0.79
     upgr
    -0.76
     ultr
    -0.73
    Ub
    -0.70
     PU
    -0.68
     vape
    -0.67
    PU
    -0.66
     Android
    -0.66
     navigation
    -0.65
     Xiaomi
    -0.64
    POSITIVE LOGITS
     Hart
    3.84
    Hart
    2.90
     Hartford
    1.36
     Holt
    1.33
     Hendricks
    1.29
     Hend
    1.20
     Hoff
    1.19
    hart
    1.16
     Feld
    1.14
     Harding
    1.11
    Activations Density 0.015%

    No Known Activations