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. 10798
    Prev
    Next
    INDEX
    Explanations

    descriptions of events and situations where things have progressed or developed

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    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
    obia
    -0.69
     Secrets
    -0.66
    hoe
    -0.64
    hell
    -0.63
    robe
    -0.61
    eln
    -0.60
    isi
    -0.60
    terday
    -0.60
     SOFTWARE
    -0.60
    itect
    -0.58
    POSITIVE LOGITS
     albeit
    1.05
     um
    0.80
     uh
    0.75
     huh
    0.74
     though
    0.72
     respectively
    0.71
    burning
    0.70
    albeit
    0.68
     namely
    0.67
     taxp
    0.64
    Activations Density 0.222%

    No Known Activations