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. 3-RES-JB
    6. 19807
    Prev
    Next
    INDEX
    Explanations

    numeric quantities or statistical information

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModLoader
    -0.84
    GBT
    -0.83
    struction
    -0.74
    IFE
    -0.74
    bey
    -0.74
    umenthal
    -0.68
    sole
    -0.67
    osi
    -0.67
    ntil
    -0.67
    termin
    -0.65
    POSITIVE LOGITS
     figures
    1.04
    hig
    0.84
    enance
    0.83
     figure
    0.82
     Figures
    0.82
    figure
    0.81
     prominently
    0.76
     Estimated
    0.76
    heet
    0.73
    estamp
    0.73
    Activations Density 0.013%

    No Known Activations