© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 9314
    Prev
    Next
    INDEX
    Explanations

    patterns of words with specific characters or structures

    oai_token-act-pair · gpt-3.5-turbo

    patterns and structures within words, particularly those involving letters and their arrangements

    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
    BuyableInstoreAndOnline
    -0.86
    Temperature
    -0.80
    artifacts
    -0.75
     Hobby
    -0.74
     Cunning
    -0.73
     Hutch
    -0.73
     Kimber
    -0.71
     Corey
    -0.71
    Gear
    -0.71
     Grimes
    -0.70
    POSITIVE LOGITS
     suffix
    1.54
     verbs
    1.50
     parentheses
    1.49
     vowel
    1.47
     comma
    1.46
     noun
    1.40
     conson
    1.39
     quotation
    1.38
     adject
    1.35
     syll
    1.33
    Activations Density 0.405%

    No Known Activations