Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5755
    Prev
    Next
    INDEX
    Explanations

    common initials used in names or titles

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns, particularly those related to people and places

    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
    ãĤº
    -0.82
    264
    -0.76
    263
    -0.74
    266
    -0.73
    udic
    -0.73
    262
    -0.73
     Americ
    -0.72
     Tycoon
    -0.72
    ãĤ¦ãĤ¹
    -0.71
     Democracy
    -0.68
    POSITIVE LOGITS
    h
    1.29
    har
    1.17
    H
    1.14
    hw
    1.11
    haw
    1.08
     HL
    1.04
    HM
    1.02
    hs
    1.01
    HT
    1.01
    HK
    1.00
    Activations Density 0.247%

    No Known Activations