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. 6-RES-JB
    6. 21627
    Prev
    Next
    INDEX
    Explanations

    sentences containing a particular punctuation mark, namely the comma

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    robe
    -0.68
    haw
    -0.60
     Companion
    -0.58
    fred
    -0.57
    iny
    -0.56
    zan
    -0.54
    boro
    -0.54
    mans
    -0.53
    chan
    -0.53
    vre
    -0.53
    POSITIVE LOGITS
     albeit
    1.27
     however
    1.09
     namely
    1.01
     whereby
    1.00
     though
    0.98
     huh
    0.93
     wherein
    0.87
    albeit
    0.86
     alas
    0.83
     therefore
    0.83
    Activations Density 0.403%

    No Known Activations