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. 19913
    Prev
    Next
    INDEX
    Explanations

    the name "Simon."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Simon."

    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
    nesday
    -0.78
    ttes
    -0.77
    ntil
    -0.76
    roxy
    -0.75
    nces
    -0.73
    acies
    -0.73
    rake
    -0.72
    ITNESS
    -0.70
    tml
    -0.69
    ĺħ
    -0.69
    POSITIVE LOGITS
     Says
    0.98
    etti
    0.91
    stown
    0.81
     Fraser
    0.77
     Gerr
    0.77
    zman
    0.76
    itars
    0.73
    sell
    0.73
     Brav
    0.73
     Simon
    0.72
    Activations Density 0.022%

    No Known Activations