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. 3-RES-JB
    6. 2514
    Prev
    Next
    INDEX
    Explanations

    legal and procedural language related to ownership, contracts, and rights

    oai_token-act-pair · gpt-3.5-turbo

    content related to legal rights and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spoiler
    -0.76
    pher
    -0.73
    thanks
    -0.73
    âĢİ
    -0.71
    Nit
    -0.70
    Chicken
    -0.70
    STAR
    -0.69
    Tel
    -0.69
    NEWS
    -0.69
    Zen
    -0.68
    POSITIVE LOGITS
     desired
    1.14
     predetermined
    1.12
     specified
    1.10
     slightest
    1.03
     wearer
    0.96
     nearest
    0.96
     lawfully
    0.95
     defective
    0.92
     corresponding
    0.92
     person
    0.90
    Activations Density 1.436%

    No Known Activations