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. 22166
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to introducing something or someone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "introduce" and its variants

    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
    die
    -0.68
    cher
    -0.68
    wiki
    -0.66
    rage
    -0.64
    otos
    -0.64
    fall
    -0.63
     workspace
    -0.63
    ache
    -0.62
    gem
    -0.62
    unker
    -0.59
    POSITIVE LOGITS
    urated
    1.02
     introduce
    0.94
     introducing
    0.87
     introduced
    0.87
    introdu
    0.87
     introduces
    0.83
     INTO
    0.73
    Introdu
    0.73
    lishes
    0.71
    ounter
    0.70
    Activations Density 0.014%

    No Known Activations