© 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. 11-RES-JB
    11. 22344
    Prev
    Next
    INDEX
    Explanations

    statements involving a conditional scenario followed by an outcome or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that address the reader directly, typically concerning actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.67
    Favorite
    -0.66
    ²¾
    -0.63
     Thomson
    -0.62
     Pant
    -0.62
    Winged
    -0.62
    Assembly
    -0.61
    UTC
    -0.61
     Comic
    -0.60
     Featured
    -0.59
    POSITIVE LOGITS
    'll
    1.19
     forfeit
    1.17
     lose
    1.16
     risk
    1.11
    're
    1.09
     incur
    1.02
     contam
    0.97
     owe
    0.96
     forfe
    0.95
     risks
    0.94
    Activations Density 0.143%

    No Known Activations