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. 2-RES-JB
    6. 183
    Prev
    Next
    INDEX
    Explanations

    the syllable 'Pat'

    oai_token-act-pair · gpt-4-turbo

    proper nouns related to the name "Pat"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Pat" or references to individuals with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.89
    hower
    -0.86
     Afric
    -0.74
    shapeshifter
    -0.72
    STD
    -0.70
    ;;;;;;;;;;;;
    -0.70
    PRES
    -0.69
     Scouting
    -0.67
     Abyssal
    -0.67
    ADE
    -0.66
    POSITIVE LOGITS
    terson
    1.06
    ented
    0.95
    hetic
    0.94
    ricks
    0.94
    riots
    0.94
    ients
    0.94
    riot
    0.92
    rice
    0.91
    rolled
    0.90
    ament
    0.90
    Activations Density 0.007%

    No Known Activations