Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15983
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    function definitions and related programming constructs in code

    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
    )</
    -0.85
    ');
    -0.84
    NI
    -0.82
    âĢ¢
    -0.80
    ");
    -0.80
     Jindal
    -0.79
     Palest
    -0.78
    ãĤ¤ãĥĪ
    -0.77
    OHN
    -0.76
    -)
    -0.76
    POSITIVE LOGITS
     """
    1.06
     def
    1.04
     print
    0.96
     self
    0.96
    raise
    0.91
     params
    0.88
     return
    0.87
     lambda
    0.80
     el
    0.79
    attr
    0.79
    Activations Density 0.088%

    No Known Activations