© 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. 7-RES-JB
    11. 22878
    Prev
    Next
    INDEX
    Explanations

    references to editorial roles in written content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "editor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bley
    -0.77
    pered
    -0.72
    achi
    -0.72
    enegger
    -0.67
    ilitary
    -0.67
    ptoms
    -0.66
    ffff
    -0.66
    00200000
    -0.62
     Fighters
    -0.62
    rises
    -0.62
    POSITIVE LOGITS
    ials
    1.28
    ially
    1.13
    ettings
    0.81
    editor
    0.80
    furt
    0.80
    iate
    0.78
    rors
    0.74
     Picks
    0.74
    hips
    0.72
    ror
    0.72
    Activations Density 0.025%

    No Known Activations