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. 9-RES-JB
    6. 21099
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     democrat
    -0.83
     indispensable
    -0.78
     compromises
    -0.72
     whatsoever
    -0.72
     irrelevant
    -0.71
     undermin
    -0.69
     fung
    -0.67
     bullshit
    -0.67
     transact
    -0.67
     stale
    -0.67
    POSITIVE LOGITS
     Initially
    1.10
     However
    1.04
     According
    1.04
     Previously
    0.99
     He
    0.99
     Asked
    0.97
     They
    0.97
     His
    0.96
     "@
    0.96
     While
    0.94
    Activations Density 0.509%

    No Known Activations