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. 0-RES-JB
    6. 21289
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the location "Kashmir."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Antiqu
    -0.85
     Sabb
    -0.69
     Administ
    -0.68
     Sting
    -0.66
     Stephenson
    -0.64
     Pompe
    -0.64
     fallout
    -0.63
     Alger
    -0.63
     Chad
    -0.63
    ourn
    -0.61
    POSITIVE LOGITS
    ku
    3.83
    zu
    2.82
    eka
    2.04
    shi
    1.81
    ju
    1.40
    kai
    1.24
    iku
    1.21
    tu
    1.17
    zhou
    1.15
    ribune
    1.11
    Activations Density 0.019%

    No Known Activations