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. 4-RES-JB
    6. 3290
    Prev
    Next
    INDEX
    Explanations

    research-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of research and investigation activities

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

    No Comments

    Negative Logits
    itol
    -0.79
     toast
    -0.71
    tering
    -0.70
     fries
    -0.64
    tall
    -0.64
     veto
    -0.62
     inherit
    -0.61
     suff
    -0.60
    arius
    -0.60
     retaliate
    -0.59
    POSITIVE LOGITS
     pse
    0.80
    ellen
    0.74
    hran
    0.71
     interviewing
    0.71
     conducted
    0.71
     factual
    0.69
     commissioned
    0.68
    berra
    0.66
     feasibility
    0.66
     uncover
    0.66
    Activations Density 0.703%

    No Known Activations