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. 1-RES-JB
    6. 18575
    Prev
    Next
    INDEX
    Explanations

    instances of words related to holding or tight grip

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "holding."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    debian
    -0.76
    gnu
    -0.71
    ettel
    -0.67
     Plain
    -0.66
    development
    -0.63
    icity
    -0.63
     Everywhere
    -0.63
    ox
    -0.63
    mph
    -0.63
     Naturally
    -0.63
    POSITIVE LOGITS
     hold
    0.93
    holders
    0.92
    pole
    0.87
    holding
    0.86
    held
    0.85
     holding
    0.85
     sway
    0.81
    holder
    0.81
     Held
    0.80
    hold
    0.79
    Activations Density 0.010%

    No Known Activations