© 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. 1-RES-JB
    11. 3912
    Prev
    Next
    INDEX
    Explanations

    special characters with diacritics indicating emphasis or emotion

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deed
    -0.77
    wig
    -0.76
    gling
    -0.74
     hybrid
    -0.63
    yon
    -0.63
    gers
    -0.62
     Prometheus
    -0.62
    wagen
    -0.62
    enstein
    -0.62
     Cass
    -0.61
    POSITIVE LOGITS
    ï
    1.43
     ï
    1.11
    cffffcc
    1.03
    Ħ¢
    0.94
    î
    0.94
    Ĥİ
    0.93
    selves
    0.87
    £
    0.83
    ĵĺ
    0.82
    Donald
    0.82
    Activations Density 0.006%

    No Known Activations