© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    words that emphasize or highlight specific content, possibly used for emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of political party identifiers or related symbols

    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
     fortun
    -0.67
     mathemat
    -0.66
     hemor
    -0.62
     misunder
    -0.62
     imitation
    -0.60
     disadvant
    -0.60
    arios
    -0.60
     Seym
    -0.59
     whiff
    -0.57
     Gutenberg
    -0.56
    POSITIVE LOGITS
    ï¸ı
    1.14
    ï¸
    0.78
    Balt
    0.74
    âĸ
    0.70
    £
    0.69
    §
    0.69
    ¯¯
    0.68
    ATH
    0.67
    âĸł
    0.67
    VERTISEMENT
    0.67
    Activations Density 0.462%

    No Known Activations