© 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. 11317
    Prev
    Next
    INDEX
    Explanations

    mentions of recent events or developments

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating recency or updates

    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
     gate
    -0.69
     tele
    -0.68
     ends
    -0.68
     hire
    -0.68
     sold
    -0.63
     beast
    -0.63
     stands
    -0.62
     magic
    -0.62
     offense
    -0.61
     cock
    -0.61
    POSITIVE LOGITS
    Recent
    3.91
     Recent
    2.05
    recent
    1.73
    Latest
    1.57
    Current
    1.50
    Recently
    1.39
    Previous
    1.37
    Past
    1.20
    Trend
    1.19
    Evidence
    1.15
    Activations Density 0.016%

    No Known Activations