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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5354
    Prev
    Next
    INDEX
    Explanations

    indications of causality or progression in a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or logical conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Causality
    thus + hence, therefore

    No Comments

    Negative Logits
    ICT
    -0.63
    dozen
    -0.58
    keyes
    -0.57
     Regions
    -0.57
    AND
    -0.57
    OSP
    -0.55
    ortment
    -0.55
    uminati
    -0.54
    abies
    -0.54
    IDs
    -0.53
    POSITIVE LOGITS
    forth
    1.92
    forward
    1.26
    far
    0.99
     far
    0.96
    ly
    0.93
    entimes
    0.83
     arises
    0.82
     arose
    0.78
     begins
    0.78
    fully
    0.77
    Activations Density 0.067%

    No Known Activations