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. 19072
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Sheldon and Stanton

    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
    alez
    -0.81
    ffic
    -0.74
    awaru
    -0.73
    ramid
    -0.73
    href
    -0.72
    opsy
    -0.72
    arily
    -0.71
    phis
    -0.71
    anwhile
    -0.69
    edo
    -0.69
    POSITIVE LOGITS
     Sheldon
    1.33
     Stern
    0.85
     Levy
    0.82
     Friedman
    0.82
     Crosby
    0.81
     Katz
    0.75
     Parsons
    0.75
     Goldstein
    0.73
     Berman
    0.73
     Cohen
    0.73
    Activations Density 0.007%

    No Known Activations