© 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. 4-RES-JB
    11. 10465
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named "Hart" in various contexts

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.92
    terday
    -0.85
     srf
    -0.78
    avorite
    -0.72
    ournal
    -0.69
    CLASSIFIED
    -0.69
     occas
    -0.65
    oulos
    -0.63
     millenn
    -0.63
    ccording
    -0.63
    POSITIVE LOGITS
    mut
    1.15
    mann
    1.12
    wig
    1.10
    enstein
    1.07
    nell
    1.00
    igan
    0.98
    lett
    0.96
    wick
    0.93
    master
    0.93
    lich
    0.92
    Activations Density 0.005%

    No Known Activations