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. 10-RES-JB
    6. 17945
    Prev
    Next
    INDEX
    Explanations

    rare or special qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating fundamental qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inhibitors
    -0.73
    mails
    -0.68
    banks
    -0.67
     lobb
    -0.67
     recommendation
    -0.62
    lations
    -0.60
     recommendations
    -0.60
    DOS
    -0.60
     fronts
    -0.58
     Annotations
    -0.58
    POSITIVE LOGITS
    antly
    1.33
    ently
    1.06
    uously
    1.03
    entimes
    1.03
    ant
    1.03
    uably
    1.01
    perty
    0.98
    et
    0.97
    ent
    0.95
    ively
    0.91
    Activations Density 0.108%

    No Known Activations