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

    Neuronpedia

    APICircuit 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. 11875
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions or criminal charges

    oai_token-act-pair · gpt-3.5-turbo

    references to legal matters and court-related issues

    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
     ain
    -0.67
    ?).
    -0.67
     [&
    -0.66
    ggles
    -0.65
    )?
    -0.64
    inventoryQuantity
    -0.64
    ¶
    -0.64
    âĶ
    -0.63
     americ
    -0.63
     darn
    -0.63
    POSITIVE LOGITS
     amid
    1.04
     although
    1.03
     (£
    1.02
     but
    0.91
     REUTERS
    0.91
     Nasa
    0.90
     prompting
    0.89
     Reuters
    0.87
     Fifa
    0.82
     because
    0.82
    Activations Density 0.964%

    No Known Activations