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. 14627
    Prev
    Next
    INDEX
    Explanations

    French words or names

    oai_token-act-pair · gpt-3.5-turbo

    words with accented characters or special diacritics

    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
    urtle
    -0.73
    okin
    -0.73
    ramid
    -0.71
    estones
    -0.69
    iary
    -0.67
    rophic
    -0.67
    regor
    -0.67
    ifier
    -0.66
    isphere
    -0.66
    icle
    -0.65
    POSITIVE LOGITS
     Lauder
    1.01
     Ãł
    0.84
    ciation
    0.83
    ée
    0.82
    tainment
    0.80
     Marie
    0.79
     dé
    0.78
    issance
    0.78
    bda
    0.73
    lement
    0.72
    Activations Density 0.010%

    No Known Activations