© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 19420
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to causes or contributing factors

    oai_token-act-pair · gpt-3.5-turbo

    discussions or mentions of contributing factors to various issues or events

    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
    netflix
    -0.79
    erity
    -0.77
    lance
    -0.74
    ocaust
    -0.73
    heid
    -0.73
    ISION
    -0.72
    ursor
    -0.72
    livion
    -0.72
    ById
    -0.72
    Dick
    -0.68
    POSITIVE LOGITS
     relate
    0.79
     characterize
    0.79
     arise
    0.79
     determining
    0.77
     mitigating
    0.75
     manifest
    0.75
     involve
    0.74
     preclude
    0.74
     affect
    0.72
     explanations
    0.72
    Activations Density 0.474%

    No Known Activations