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. 19620
    Prev
    Next
    INDEX
    Explanations

    names or mentions of individuals named "Howard."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Howard."

    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
    Zero
    -0.72
    rx
    -0.70
    fal
    -0.69
    terday
    -0.68
    ktop
    -0.66
    boarding
    -0.63
    erala
    -0.63
    xual
    -0.60
    pmwiki
    -0.59
    cv
    -0.58
    POSITIVE LOGITS
     Stern
    1.13
     Hughes
    0.94
     Schultz
    0.88
     Stark
    0.82
     Schn
    0.78
     Dean
    0.77
     Jarvis
    0.77
    sonian
    0.76
    gdala
    0.73
     Sachs
    0.73
    Activations Density 0.034%

    No Known Activations