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. 10-RES-JB
    6. 18097
    Prev
    Next
    INDEX
    Explanations

    names or terms starting with "Mc"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mc" followed by various letters, likely indicating a focus on people's last names or mentions in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unprotected
    -0.77
     misunderstood
    -0.72
    ãĥĥãĥĪ
    -0.69
     deaf
    -0.66
     ACS
    -0.65
     mistaken
    -0.65
     partName
    -0.64
     Acts
    -0.64
     provoking
    -0.62
     downt
    -0.62
    POSITIVE LOGITS
    Afee
    1.51
    intosh
    1.40
    Leod
    1.34
    Connell
    1.33
    artney
    1.27
    Donald
    1.21
    Bride
    1.21
    Lean
    1.21
    Kin
    1.20
    Donnell
    1.18
    Activations Density 0.012%

    No Known Activations