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. 11-RES-JB
    6. 8084
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names like "Brian"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Brian."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.67
    minist
    -0.61
    roxy
    -0.58
     ranged
    -0.57
     includ
    -0.56
     relative
    -0.56
    ixed
    -0.56
    affe
    -0.56
    iction
    -0.55
    INS
    -0.55
    POSITIVE LOGITS
     Nose
    0.91
     Blessed
    0.85
     Fallon
    0.85
     McCann
    0.82
     Fitzpatrick
    0.81
     Moy
    0.79
    ne
    0.79
    ãĥ£
    0.78
     Deer
    0.78
    terness
    0.76
    Activations Density 0.036%

    No Known Activations