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. 7-RES-JB
    6. 8094
    Prev
    Next
    INDEX
    Explanations

    keywords related to data, collection, and information

    oai_token-act-pair · gpt-3.5-turbo

    references to "data" in various contexts related to technology and information processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModLoader
    -0.89
    lain
    -0.80
     Oath
    -0.80
    ength
    -0.77
    ovie
    -0.73
    folios
    -0.70
     Nicarag
    -0.69
    nen
    -0.68
    aska
    -0.68
     Ascend
    -0.67
    POSITIVE LOGITS
    flow
    1.08
    iologist
    0.97
     analytics
    0.95
    frame
    0.88
     recorder
    0.85
    Transfer
    0.85
     collection
    0.82
    flows
    0.81
    minist
    0.81
    dump
    0.78
    Activations Density 0.034%

    No Known Activations