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. 8-RES-JB
    6. 22199
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or statistics of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deed
    -0.64
    :(
    -0.62
     deeds
    -0.60
     streng
    -0.60
     plat
    -0.58
     compan
    -0.58
     marqu
    -0.57
     Became
    -0.57
     proposition
    -0.57
    enhagen
    -0.57
    POSITIVE LOGITS
    000
    1.68
    500
    1.17
    700
    1.15
    900
    1.10
    600
    1.09
    800
    1.08
    00
    1.07
    400
    1.04
    300
    1.03
    200
    0.94
    Activations Density 0.084%

    No Known Activations