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. 21920
    Prev
    Next
    INDEX
    Explanations

    Proper names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of people or proper nouns

    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
    dayName
    -0.91
    tymology
    -0.86
    gencies
    -0.83
    Äĩ
    -0.80
    rosis
    -0.78
    atical
    -0.77
    glers
    -0.77
    haps
    -0.77
    asus
    -0.76
    fecture
    -0.76
    POSITIVE LOGITS
     Stewart
    1.19
     McKenzie
    1.18
     Dixon
    1.17
     Peters
    1.17
     Reed
    1.17
     Henderson
    1.17
     Cunningham
    1.14
     McK
    1.12
     Carter
    1.12
     Simmons
    1.12
    Activations Density 0.205%

    No Known Activations