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. 9-RES-JB
    6. 12128
    Prev
    Next
    INDEX
    Explanations

    titles or labels of media content and products

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     handlers
    -0.74
     impeachment
    -0.74
     appreci
    -0.72
     spir
    -0.72
     hydrogen
    -0.69
     buoy
    -0.67
     disg
    -0.67
     confront
    -0.67
     electr
    -0.67
     inund
    -0.66
    POSITIVE LOGITS
    includes
    1.44
    optional
    1.43
    formerly
    1.42
    feat
    1.34
    Includes
    1.29
    via
    1.24
    Optional
    1.24
    excluding
    1.22
    ?)
    1.21
    requires
    1.20
    Activations Density 0.116%

    No Known Activations