© 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. 7-RES-JB
    6. 15362
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation or explanation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causality or reasons

    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
    marine
    -0.66
     benches
    -0.66
    erers
    -0.65
    ullivan
    -0.64
    erella
    -0.58
    iers
    -0.58
    rone
    -0.58
    earchers
    -0.56
    antes
    -0.56
     Barclays
    -0.56
    POSITIVE LOGITS
     foregoing
    0.67
    math
    0.67
     disclaimer
    0.67
     disclaim
    0.65
     coincidence
    0.63
     perverse
    0.61
    ç¥ŀ
    0.61
     inexper
    0.60
     reporting
    0.60
     confusion
    0.60
    Activations Density 0.156%

    No Known Activations