Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 246
    Prev
    Next
    INDEX
    Explanations

    HTML code snippets containing specific classes or IDs

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming or code structure

    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
     Kurdistan
    -0.85
     Til
    -0.84
     Anglic
    -0.79
     Noon
    -0.78
     Rams
    -0.72
     Hell
    -0.72
     680
    -0.72
     820
    -0.71
     Trin
    -0.70
     Liberation
    -0.70
    POSITIVE LOGITS
    name
    1.40
    message
    1.37
    title
    1.36
    input
    1.36
    username
    1.33
    primary
    1.29
    parent
    1.28
    user
    1.28
    condition
    1.26
    content
    1.25
    Activations Density 0.071%

    No Known Activations