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. 7-RES-JB
    6. 10319
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period and a high emphasis expression

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and commas, indicating sentence endings and pauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meier
    -0.71
     Archangel
    -0.69
    iden
    -0.68
     Archdemon
    -0.68
    ensen
    -0.67
     Ames
    -0.64
    ãĥĭ
    -0.63
    âĹ¼
    -0.63
    manship
    -0.63
    idious
    -0.61
    POSITIVE LOGITS
    Interstitial
    1.25
    taboola
    0.95
    til
    0.82
    tis
    0.81
    Cause
    0.79
    neath
    0.79
    cause
    0.77
    Mech
    0.76
     ',
    0.72
    auga
    0.71
    Activations Density 0.053%

    No Known Activations