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. 9-RES-JB
    6. 12884
    Prev
    Next
    INDEX
    Explanations

    measurements of physical quantities

    oai_token-act-pair · gpt-3.5-turbo

    units of measurement and their associated values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.66
    manship
    -0.62
    bidden
    -0.61
    estate
    -0.60
    naissance
    -0.60
     advising
    -0.60
     marqu
    -0.58
    furt
    -0.58
     Valentine
    -0.58
     lookout
    -0.57
    POSITIVE LOGITS
    pees
    1.05
    pi
    1.00
    ms
    0.99
    pm
    0.96
    Pa
    0.96
    pg
    0.91
    awatts
    0.91
    wt
    0.90
    abytes
    0.89
    illion
    0.88
    Activations Density 0.092%

    No Known Activations