© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9958
    Prev
    Next
    INDEX
    Explanations

    personal experiences or stories shared by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals mentioning their experiences

    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
    tu
    -0.69
    isoft
    -0.68
    ģĸ
    -0.67
    mite
    -0.67
    emort
    -0.63
    ez
    -0.62
    Released
    -0.61
    isons
    -0.61
    ption
    -0.59
    irements
    -0.57
    POSITIVE LOGITS
     privately
    1.02
     bluntly
    1.01
     beforehand
    0.88
     anecd
    0.87
     repeatedly
    0.86
     plainly
    0.85
     personally
    0.84
     emphatically
    0.83
     afterward
    0.81
     afterwards
    0.79
    Activations Density 0.037%

    No Known Activations