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. 7-RES-JB
    6. 21040
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific entities, particularly those related to popular culture, sports, and current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.65
    jri
    -0.50
     Democr
    -0.50
    Ire
    -0.50
    ij士
    -0.48
     destro
    -0.48
     Azerb
    -0.48
     Vaugh
    -0.47
    nil
    -0.47
     prest
    -0.47
    POSITIVE LOGITS
    ¶
    0.47
    weed
    0.47
     âĢº
    0.46
    illion
    0.43
     reacts
    0.42
     enters
    0.42
     ][
    0.42
    hon
    0.40
    going
    0.39
     microbiome
    0.38
    Activations Density 0.866%

    No Known Activations