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. 11-RES-JB
    6. 17994
    Prev
    Next
    INDEX
    Explanations

    phrases related to company product launches and corporate announcements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific special character or symbol used in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     walking
    -0.74
     swept
    -0.72
     bed
    -0.71
     Glou
    -0.71
     beck
    -0.70
     step
    -0.69
     staggered
    -0.69
     Triangle
    -0.68
     kne
    -0.68
    stood
    -0.66
    POSITIVE LOGITS
    ¬
    1.31
    Ĵ
    1.29
    ı
    1.26
    ħ
    1.23
    ¡
    1.23
    IJ
    1.21
    ¤
    1.20
    ª
    1.19
    ĺ
    1.17
    Ń
    1.15
    Activations Density 0.181%

    No Known Activations