Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 1711
    Prev
    Next
    INDEX
    Explanations

    mentions of technology products and models

    oai_token-act-pair · gpt-3.5-turbo

    references to the "One" brand or product name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="#
    -0.72
    lished
    -0.71
    ucl
    -0.70
    ruary
    -0.66
    ordes
    -0.65
     actionGroup
    -0.64
    ulative
    -0.63
    aeda
    -0.63
    ãĥ¼
    -0.62
    apons
    -0.62
    POSITIVE LOGITS
     Hundred
    1.04
     Thousand
    0.84
     Million
    0.82
     dimensional
    0.80
     Direction
    0.79
    Drive
    0.78
    esan
    0.77
     hundred
    0.75
    Shot
    0.75
    elf
    0.75
    Activations Density 0.085%

    No Known Activations