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. 3744
    Prev
    Next
    INDEX
    Explanations

    the last names of celebrities or famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific names and proper nouns, particularly those related to people or characters

    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
    •EggList

    No Comments

    Negative Logits
    ãĤ¬
    -0.84
     CAP
    -0.77
     ESA
    -0.74
     arrang
    -0.72
     poss
    -0.70
     Manit
    -0.70
     DIRECT
    -0.70
     Cort
    -0.70
     Equip
    -0.70
     helicop
    -0.69
    POSITIVE LOGITS
    y
    1.46
    ys
    1.31
    yon
    1.30
    yles
    1.29
    yx
    1.28
    Y
    1.27
    yl
    1.25
    yan
    1.21
    yg
    1.19
    ym
    1.16
    Activations Density 0.271%

    No Known Activations