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. 6-RES-JB
    6. 6173
    Prev
    Next
    INDEX
    Explanations

    names, particularly the name "Mark"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Mark"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decomp
    -0.74
    urses
    -0.74
     adolesc
    -0.72
    dayName
    -0.70
    pmwiki
    -0.68
    Interstitial
    -0.67
     nerv
    -0.67
    cffffcc
    -0.67
     traged
    -0.66
    ategory
    -0.66
    POSITIVE LOGITS
     Twain
    1.15
     Zuckerberg
    1.06
    eting
    1.03
    edly
    0.95
    owitz
    0.94
    eters
    0.94
    down
    0.93
    ipl
    0.88
    wayne
    0.86
    furt
    0.84
    Activations Density 0.021%

    No Known Activations