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. 3-RES-JB
    6. 14421
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name or place, "Söder.”

    oai_token-act-pair · gpt-3.5-turbo

    variations of a specific character or symbol within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entirety
    -0.77
    xual
    -0.72
     Drawn
    -0.64
     Hercules
    -0.63
    riott
    -0.62
    aneously
    -0.61
    enged
    -0.61
     Gemini
    -0.61
    aneous
    -0.60
     Sasuke
    -0.59
    POSITIVE LOGITS
    ö
    1.20
    ·
    1.11
    ¶
    1.02
    ä
    0.96
    ¬
    0.95
    ön
    0.95
    zbek
    0.92
    ¸
    0.92
    Ķ
    0.92
    å
    0.92
    Activations Density 0.006%

    No Known Activations