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. 10-RES-JB
    6. 13011
    Prev
    Next
    INDEX
    Explanations

    phrases with a sense of finality or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     representatives
    -0.77
     affili
    -0.74
     substantive
    -0.72
     policies
    -0.69
     eligibility
    -0.69
     assessments
    -0.68
     acknowled
    -0.66
     commitments
    -0.66
     contributions
    -0.65
     aggreg
    -0.65
    POSITIVE LOGITS
    wav
    1.01
    jpg
    0.97
    gif
    0.97
     Sounds
    0.90
    cue
    0.87
     Yeah
    0.85
     Yep
    0.84
     Literally
    0.84
     huh
    0.83
     Nope
    0.82
    Activations Density 0.477%

    No Known Activations