Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 4128
    Prev
    Next
    INDEX
    Explanations

    mentions of do-it-yourself (DIY) activities or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to DIY (do-it-yourself) culture and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.95
    ority
    -0.85
    istics
    -0.78
     Ambrose
    -0.77
     Archdemon
    -0.76
    ivia
    -0.70
    awar
    -0.70
    orr
    -0.69
     Osw
    -0.68
    words
    -0.67
    POSITIVE LOGITS
     DIY
    1.01
    IED
    0.95
     calcul
    0.95
    ModLoader
    0.80
     nomine
    0.71
    sonian
    0.70
    DI
    0.70
     hobby
    0.70
    LV
    0.69
     homemade
    0.68
    Activations Density 0.005%

    No Known Activations