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. 8-RES-JB
    6. 21046
    Prev
    Next
    INDEX
    Explanations

    references to the word "ball"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'ball' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.72
    ãĥ´
    -0.67
     Ples
    -0.66
    åİ
    -0.65
    ript
    -0.64
     Merchants
    -0.63
    éĥ
    -0.61
    liness
    -0.61
     plur
    -0.61
     showc
    -0.60
    POSITIVE LOGITS
    istics
    1.19
    oons
    1.00
    ball
    0.98
    ghazi
    0.94
    oon
    0.92
    haus
    0.91
    istically
    0.90
    player
    0.89
    asted
    0.88
    park
    0.88
    Activations Density 0.026%

    No Known Activations