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. 10-RES-JB
    6. 19230
    Prev
    Next
    INDEX
    Explanations

    relationships between various medical conditions or physiological aspects

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly commas, as indicators of complex sentence structures or lists

    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
    ãĥīãĥ©
    -0.69
     Welcome
    -0.64
    arantine
    -0.62
    ¬¼
    -0.60
     Scream
    -0.60
    mire
    -0.57
     hassle
    -0.57
    vernight
    -0.56
    walk
    -0.56
    rero
    -0.55
    POSITIVE LOGITS
     whereas
    1.40
     suggesting
    1.35
     implying
    1.30
     indicating
    1.30
     namely
    1.23
     thereby
    1.22
     although
    1.19
     hence
    1.15
     resulting
    1.14
     whereby
    1.13
    Activations Density 0.279%

    No Known Activations