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. 10-RES-JB
    6. 15325
    Prev
    Next
    INDEX
    Explanations

    legal and administrative terms with hyphens and special characters

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with legal or formal notices and documentation

    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
     circles
    -0.93
     dinosaurs
    -0.90
     Tycoon
    -0.86
     landscapes
    -0.82
     bubbles
    -0.82
     mushrooms
    -0.82
     heights
    -0.78
     dwarves
    -0.78
     galaxies
    -0.78
     hordes
    -0.77
    POSITIVE LOGITS
     waiver
    1.34
    statement
    1.27
    license
    1.26
    untary
    1.25
     revocation
    1.22
    endment
    1.21
     exemption
    1.20
     consent
    1.17
    emption
    1.17
     authorization
    1.17
    Activations Density 0.345%

    No Known Activations