© 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. 12-RES-JB
    11. 4561
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to evidence and allegations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that suggest a lack of evidence or support for claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.86
    received
    -0.77
    Got
    -0.75
     ado
    -0.71
    iasis
    -0.71
    angered
    -0.70
    externalActionCode
    -0.69
    glomer
    -0.68
    heard
    -0.67
     Wanted
    -0.67
    POSITIVE LOGITS
     support
    1.32
     refute
    1.31
     substant
    1.30
     suggest
    1.24
     prove
    1.21
     dispro
    1.20
     demonstrate
    1.20
     justify
    1.19
     corrobor
    1.18
     indicate
    1.13
    Activations Density 0.165%

    No Known Activations