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. 1240
    Prev
    Next
    INDEX
    Explanations

    statements of importance or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the use of punctuation, particularly periods and their frequency in relation to various topics

    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
     tyr
    -0.79
     quir
    -0.79
     hug
    -0.78
     ugly
    -0.73
     gobl
    -0.72
     instinct
    -0.72
     footing
    -0.71
     unstoppable
    -0.70
     nodd
    -0.68
     grip
    -0.67
    POSITIVE LOGITS
     Additionally
    1.47
     Furthermore
    1.36
     However
    1.35
     Accordingly
    1.34
     Therefore
    1.32
     Moreover
    1.30
     Consequently
    1.28
     Similarly
    1.24
     Alternatively
    1.22
     Likewise
    1.21
    Activations Density 1.457%

    No Known Activations