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. 0-RES-JB
    6. 22043
    Prev
    Next
    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Jacob."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PU
    -0.72
    ãĤĬ
    -0.70
     Okinawa
    -0.69
    Sea
    -0.67
     Samurai
    -0.66
    resy
    -0.64
    tail
    -0.64
    service
    -0.64
     Okin
    -0.64
     Anime
    -0.62
    POSITIVE LOGITS
     Jacob
    3.55
    Jacob
    3.17
    Jac
    1.56
     Isaac
    1.50
     Abraham
    1.32
     Judah
    1.31
     Jacobs
    1.30
    jac
    1.28
     Joseph
    1.25
     Zach
    1.24
    Activations Density 0.016%

    No Known Activations