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. 3-RES-JB
    6. 7555
    Prev
    Next
    INDEX
    Explanations

    the word "entire" within sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "entire."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kick
    -0.69
    inel
    -0.67
    ker
    -0.66
    po
    -0.65
    asta
    -0.64
    bid
    -0.64
    ador
    -0.63
    Blade
    -0.63
    ju
    -0.63
     advoc
    -0.62
    POSITIVE LOGITS
    heartedly
    1.05
    hearted
    0.78
    ciating
    0.76
     entire
    0.72
     gam
    0.70
    foundland
    0.69
    ODUCT
    0.69
    uania
    0.69
     spectrum
    0.67
     contents
    0.67
    Activations Density 0.017%

    No Known Activations