© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17371
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of where to find various resources or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating where to locate information or resources

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

    No Comments

    Negative Logits
    rang
    -0.74
    ework
    -0.61
    assisted
    -0.60
     endeavour
    -0.58
     endeav
    -0.58
     precaution
    -0.58
     fueled
    -0.57
    iazep
    -0.57
     Ambro
    -0.56
     Reboot
    -0.55
    POSITIVE LOGITS
     plenty
    0.79
    ById
    0.76
    NEWS
    0.74
    MAG
    0.68
    FORE
    0.67
    lopp
    0.67
     ample
    0.64
    ATIONS
    0.64
    vre
    0.62
    abella
    0.62
    Activations Density 0.116%

    No Known Activations