© 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. 10-RES-JB
    11. 14117
    Prev
    Next
    INDEX
    Explanations

    mentions of enabling or disabling different features or settings, particularly in relation to technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enabling and disabling features or settings in devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apest
    -0.98
    ioxide
    -0.92
    axies
    -0.86
    enegger
    -0.83
    nant
    -0.79
    sworth
    -0.77
    llah
    -0.72
    esta
    -0.72
    rio
    -0.70
    iday
    -0.70
    POSITIVE LOGITS
     automatic
    0.93
     javascript
    0.85
     caching
    0.79
     Automatic
    0.77
     anonymity
    0.77
     HTTPS
    0.76
    ment
    0.73
     Javascript
    0.73
     debugging
    0.72
     debug
    0.69
    Activations Density 0.046%

    No Known Activations