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. 8-RES-JB
    6. 19249
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to current events and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people, places, and cultures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.70
    oppable
    -0.69
     prest
    -0.68
     Niet
    -0.58
    sit
    -0.58
    enegger
    -0.56
    /,
    -0.55
    akespe
    -0.54
    ãĥ¼ãĥĨ
    -0.54
    ilaterally
    -0.54
    POSITIVE LOGITS
     reacts
    0.65
     celebrates
    0.58
     )))
    0.57
     ][
    0.57
     ::
    0.55
     approves
    0.55
     Moves
    0.54
     Motors
    0.54
     Brewing
    0.53
     ãĥ
    0.53
    Activations Density 0.324%

    No Known Activations