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. 3715
    Prev
    Next
    INDEX
    Explanations

    the word "beige"

    oai_token-act-pair · gpt-3.5-turbo

    references to "eigen" and related mathematical or computational concepts

    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
     services
    -0.62
     prayers
    -0.61
     parts
    -0.60
     Doors
    -0.59
     Rochester
    -0.59
     floods
    -0.58
     Reuters
    -0.57
     surf
    -0.57
     Sur
    -0.57
     core
    -0.56
    POSITIVE LOGITS
    ige
    4.64
    ig
    1.62
    igen
    1.56
    iga
    1.34
    iger
    1.33
    igious
    1.27
    igo
    1.22
    igs
    1.21
    igans
    1.15
    igers
    1.12
    Activations Density 0.013%

    No Known Activations