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. 1-RES-JB
    6. 19694
    Prev
    Next
    INDEX
    Explanations

    Pacific Island countries or territories

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of places and individuals

    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
    âķIJâķIJ
    -0.81
    ICAN
    -0.81
     Elys
    -0.74
    print
    -0.70
    è¦ļéĨĴ
    -0.69
     GOODMAN
    -0.69
    ICO
    -0.66
     Pathfinder
    -0.65
    ACP
    -0.65
    VEL
    -0.64
    POSITIVE LOGITS
     Tong
    1.34
    ues
    0.94
    ueless
    0.92
    atu
    0.92
    sung
    0.88
     tong
    0.87
    ratulations
    0.85
    ingen
    0.81
    ecided
    0.79
    hiba
    0.78
    Activations Density 0.014%

    No Known Activations