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. 11-RES-JB
    6. 19448
    Prev
    Next
    INDEX
    Explanations

    experiences, phenomena, or concepts associated with expansion or growth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expansion" or its variations

    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
    âĸ¬
    -0.75
    ball
    -0.73
    ãĥ£
    -0.71
    âĸ¬âĸ¬
    -0.69
    balls
    -0.68
    milo
    -0.68
     thumbs
    -0.67
     behind
    -0.63
     Bene
    -0.60
     hearts
    -0.58
    POSITIVE LOGITS
    ansion
    1.67
    onential
    1.67
    anding
    1.57
    anded
    1.53
    onent
    1.51
    ression
    1.40
    osed
    1.40
    ressive
    1.37
    ensive
    1.36
    ressed
    1.30
    Activations Density 0.021%

    No Known Activations