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. 7-RES-JB
    6. 16315
    Prev
    Next
    INDEX
    Explanations

    companies or entities based in specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to locations associated with organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ν
    -0.70
    dimension
    -0.67
    helm
    -0.67
    nob
    -0.66
    idences
    -0.66
    alid
    -0.66
    é¾įå
    -0.64
    Putin
    -0.64
    spir
    -0.63
    heart
    -0.63
    POSITIVE LOGITS
    quartered
    1.20
     businessman
    0.94
     entrepreneur
    0.90
     nonprofit
    0.90
     filmmaker
    0.80
     multinational
    0.78
     resident
    0.78
     freelance
    0.78
     photographer
    0.76
     artist
    0.76
    Activations Density 0.045%

    No Known Activations