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. 0-RES-JB
    6. 6104
    Prev
    Next
    INDEX
    Explanations

    references to physically holding or gripping something

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "hold" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otyp
    -0.68
    ocom
    -0.66
    ines
    -0.63
    chrom
    -0.62
    é»Ĵ
    -0.62
    erson
    -0.62
    bats
    -0.61
    article
    -0.61
    ony
    -0.60
     IPM
    -0.58
    POSITIVE LOGITS
     hold
    3.59
    hold
    2.23
     Hold
    2.12
     holds
    2.05
    Hold
    1.85
     holding
    1.77
     grip
    1.68
     held
    1.61
     grasp
    1.47
     foothold
    1.33
    Activations Density 0.013%

    No Known Activations