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. 7-RES-JB
    6. 19725
    Prev
    Next
    INDEX
    Explanations

    proper nouns containing the sequence "u" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'u' in varying frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horizont
    -0.77
    =-=-
    -0.70
     Attribution
    -0.69
     therap
    -0.67
    20439
    -0.66
     Payton
    -0.66
     initials
    -0.65
     Cosponsors
    -0.63
     CBI
    -0.63
     constants
    -0.62
    POSITIVE LOGITS
    pport
    1.29
    cca
    1.27
    ccess
    1.15
    pta
    1.09
    itton
    1.05
    cius
    1.05
    pling
    1.03
    seless
    1.02
    hiro
    1.02
    isine
    1.01
    Activations Density 0.045%

    No Known Activations