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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 18266
    Prev
    Next
    INDEX
    Explanations

    mentions of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize quantity or reference large portions of information

    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
    cards
    -0.91
    ples
    -0.88
    rants
    -0.82
    ciation
    -0.81
    holes
    -0.80
    few
    -0.80
    laws
    -0.79
    chairs
    -0.79
    bags
    -0.77
    eps
    -0.74
    POSITIVE LOGITS
     southeastern
    0.80
     southwestern
    0.77
     blame
    0.76
     attention
    0.76
     misinformation
    0.76
     southern
    0.76
     what
    0.75
     groundwork
    0.74
     Silicon
    0.74
     northeastern
    0.73
    Activations Density 0.103%

    No Known Activations