© 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. 9230
    Prev
    Next
    INDEX
    Explanations

    specific formatting cues such as section breaks or special characters

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and references related to software, programming, or file handling

    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
     foul
    -0.90
     eleph
    -0.90
     buoy
    -0.85
     creep
    -0.82
     waged
    -0.81
     youthful
    -0.80
     pione
    -0.80
     paddle
    -0.80
     dwell
    -0.79
     roller
    -0.79
    POSITIVE LOGITS
    Usage
    1.89
    Example
    1.83
    Installation
    1.81
    Examples
    1.76
    License
    1.76
    Creating
    1.74
    Conclusion
    1.71
    Using
    1.71
    Requirements
    1.71
    Contribut
    1.69
    Activations Density 0.156%

    No Known Activations