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. 358
    Prev
    Next
    INDEX
    Explanations

    phrases related to single, multiplayer, and family settings in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to single-family units and their characteristics

    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
     Richards
    -0.75
     Zar
    -0.73
     Wolfgang
    -0.64
     Irma
    -0.64
    ORK
    -0.63
     Tart
    -0.62
     Shaw
    -0.60
     McKin
    -0.60
     cartoons
    -0.59
     Faust
    -0.59
    POSITIVE LOGITS
    handedly
    1.39
    digit
    1.34
    minded
    1.31
    sided
    1.29
    player
    1.17
    occup
    1.15
    family
    1.13
    issue
    1.12
    handed
    1.11
    unit
    1.09
    Activations Density 0.023%

    No Known Activations