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. 16584
    Prev
    Next
    INDEX
    Explanations

    names of people and their associated professions or actions

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically for individuals or entities

    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
     Saiyan
    -0.64
     RELE
    -0.60
     issu
    -0.60
     DISTRICT
    -0.58
     guiActiveUnfocused
    -0.57
    Products
    -0.56
    unker
    -0.54
     experien
    -0.54
     MID
    -0.54
    ULE
    -0.53
    POSITIVE LOGITS
     whom
    0.90
     him
    0.88
     teammate
    0.78
     hers
    0.77
    him
    0.77
    aus
    0.73
     classmate
    0.72
    his
    0.70
     Jr
    0.68
    CHAT
    0.66
    Activations Density 1.095%

    No Known Activations