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. 5496
    Prev
    Next
    INDEX
    Explanations

    weights given to various aspects or entities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to efforts, weight, and importance in discussions

    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
     Avenger
    -0.67
     lookout
    -0.67
     cowork
    -0.63
    wagen
    -0.62
     2025
    -0.62
    ãĤ´ãĥ³
    -0.59
    CHAT
    -0.59
     Massacre
    -0.58
     operative
    -0.57
     quint
    -0.57
    POSITIVE LOGITS
    flex
    0.91
    NH
    0.77
     than
    0.75
    fulness
    0.73
    aic
    0.72
     nowadays
    0.71
     mileage
    0.67
    enance
    0.67
     whatsoever
    0.66
    idious
    0.66
    Activations Density 0.278%

    No Known Activations