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. 22873
    Prev
    Next
    INDEX
    Explanations

    terms related to achievements and successes in different fields such as sports, military, and academia

    oai_token-act-pair · gpt-3.5-turbo

    references to sports or athletic accomplishments

    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
    */(
    -0.64
     nonetheless
    -0.61
    morrow
    -0.60
     tonight
    -0.60
    cellaneous
    -0.58
     GOODMAN
    -0.58
     sqor
    -0.58
    rawdownloadcloneembedreportprint
    -0.55
     Patreon
    -0.55
    channelAvailability
    -0.54
    POSITIVE LOGITS
    Ö¼
    0.58
     Afgh
    0.53
    oslov
    0.53
    BuyableInstoreAndOnline
    0.52
    Ü
    0.52
    ago
    0.50
    inosaur
    0.49
    IJ
    0.49
     Atari
    0.48
     predecessor
    0.48
    Activations Density 1.113%

    No Known Activations