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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9332
    Prev
    Next
    INDEX
    Explanations

    mentions of "Ball" as a significant entity or reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to the term "Ball" with varying activations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liness
    -0.72
     profit
    -0.66
    ths
    -0.65
    éĹĺ
    -0.64
    terday
    -0.63
    æĢ
    -0.62
    CRIP
    -0.61
    ktop
    -0.61
    åº
    -0.60
    iosyncr
    -0.59
    POSITIVE LOGITS
    oons
    1.24
    park
    1.00
    oon
    0.96
    aign
    0.92
    arat
    0.91
    antine
    0.88
    haus
    0.88
    istics
    0.87
    assic
    0.83
    asts
    0.83
    Activations Density 0.010%

    No Known Activations