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. 1-RES-JB
    6. 8420
    Prev
    Next
    INDEX
    Explanations

    instances of commas followed by various symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of comma usage and rhetorical pauses in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.68
    iple
    -0.68
    herent
    -0.64
     metic
    -0.60
    terness
    -0.60
     redes
    -0.58
    manac
    -0.58
    estones
    -0.58
     elite
    -0.56
    OND
    -0.55
    POSITIVE LOGITS
     albeit
    0.99
     namely
    0.90
     although
    0.89
     however
    0.87
     though
    0.79
    Downloadha
    0.77
     alas
    0.77
     except
    0.76
     etc
    0.75
     whereas
    0.74
    Activations Density 1.566%

    No Known Activations