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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 21277
    Prev
    Next
    INDEX
    Explanations

    names of people or places beginning with 'Den'

    oai_token-act-pair · gpt-3.5-turbo

    specific noun and adjective combinations related to names or labels

    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
    yahoo
    -0.69
    è¦ļéĨĴ
    -0.65
    ebus
    -0.64
    arella
    -0.63
    pport
    -0.63
     hoops
    -0.63
    CHO
    -0.63
     moms
    -0.63
    mercial
    -0.62
     Pwr
    -0.61
    POSITIVE LOGITS
    ciating
    0.75
    rences
    0.74
    puff
    0.72
    Pont
    0.69
    rays
    0.67
    issance
    0.65
    Lewis
    0.65
    ukes
    0.65
    heed
    0.64
    enment
    0.64
    Activations Density 0.187%

    No Known Activations