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. 9-RES-JB
    6. 327
    Prev
    Next
    INDEX
    Explanations

    phrases that are commonly used in research or formal reports

    oai_token-act-pair · gpt-3.5-turbo

    references to research studies or reports about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favour
    -0.81
     covenant
    -0.80
     babe
    -0.80
     audition
    -0.79
     inspir
    -0.79
     protector
    -0.79
     asshole
    -0.78
     ornament
    -0.78
     reflex
    -0.77
     guy
    -0.77
    POSITIVE LOGITS
    ccording
    1.43
    Additionally
    1.33
    Similarly
    1.30
    However
    1.29
    Among
    1.28
    Previously
    1.27
    According
    1.23
    Furthermore
    1.21
    Experts
    1.21
    Moreover
    1.20
    Activations Density 0.271%

    No Known Activations