© 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. 1-RES-JB
    6. 16772
    Prev
    Next
    INDEX
    Explanations

    strings containing the letter "C" followed by a specific single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "C" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.82
    EStream
    -0.80
     Tinder
    -0.79
    DragonMagazine
    -0.77
    ãĥĦ
    -0.76
    ãĥŀ
    -0.74
    terday
    -0.72
     Wrestle
    -0.69
    Magikarp
    -0.68
    ItemTracker
    -0.68
    POSITIVE LOGITS
    overed
    1.25
    abbage
    1.04
    oding
    1.04
    ursor
    1.03
    rouch
    1.00
    resp
    1.00
    olly
    0.99
    heddar
    0.97
    VC
    0.95
    rawl
    0.94
    Activations Density 0.035%

    No Known Activations