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. 0-RES-JB
    6. 6021
    Prev
    Next
    INDEX
    Explanations

    Turkish characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or set of characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LS
    -0.69
     Mara
    -0.68
     multiplier
    -0.67
     Ingram
    -0.67
     Ballard
    -0.66
     Coliseum
    -0.66
     Vaughn
    -0.65
     Livingston
    -0.64
     Raider
    -0.63
     captains
    -0.63
    POSITIVE LOGITS
    ü
    4.10
    ür
    2.15
    ö
    2.13
    ön
    1.93
    ä
    1.87
     Mü
    1.81
    ı
    1.66
    ör
    1.57
    Ã
    1.50
     Ãĸ
    1.47
    Activations Density 0.008%

    No Known Activations