© 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. 8-RES-JB
    11. 10059
    Prev
    Next
    INDEX
    Explanations

    government-related terms, such as committees, agencies, departments, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical studies and surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     awa
    -0.70
     seiz
    -0.65
     TAMADRA
    -0.64
     cos
    -0.61
     dearly
    -0.60
    cause
    -0.59
    ());
    -0.57
     tsun
    -0.57
    aah
    -0.57
    ]);
    -0.56
    POSITIVE LOGITS
     illustrates
    0.98
     titled
    0.92
     indicates
    0.91
    published
    0.90
     suggests
    0.89
     dated
    0.87
     reveals
    0.86
     detailing
    0.85
    anmar
    0.85
     underscores
    0.82
    Activations Density 0.485%

    No Known Activations