© 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. 10-RES-JB
    11. 20198
    Prev
    Next
    INDEX
    Explanations

    statements of causality or rules

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that establish relationships between clauses or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.84
    swick
    -0.74
    daq
    -0.70
    grim
    -0.69
    wow
    -0.65
    Fram
    -0.64
    NetMessage
    -0.64
    auntlet
    -0.64
    Animation
    -0.63
    soType
    -0.63
    POSITIVE LOGITS
     whenever
    1.29
     anyone
    1.20
     whoever
    1.17
     every
    1.13
     whichever
    1.11
     each
    1.10
     if
    1.09
     individuals
    1.08
     any
    1.07
     anybody
    1.01
    Activations Density 0.372%

    No Known Activations