© 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. 0-RES-JB
    11. 5317
    Prev
    Next
    INDEX
    Explanations

    mentions of someone's background or history

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or contextual backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ames
    -0.76
    aches
    -0.76
    hered
    -0.74
    ques
    -0.72
    efficient
    -0.72
    Eat
    -0.68
    iom
    -0.67
    rists
    -0.64
    ievers
    -0.63
    selling
    -0.62
    POSITIVE LOGITS
     background
    4.26
     Background
    2.79
    background
    2.62
     backgrounds
    2.60
     backdrop
    2.28
     foreground
    2.17
    Background
    1.91
     backstory
    1.42
     context
    1.11
     upbringing
    1.06
    Activations Density 0.011%

    No Known Activations