© 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. 21153
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to businesses, organizations, or places

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations, locations, or entities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.90
    isSpecialOrderable
    -0.76
    */(
    -0.74
    inventoryQuantity
    -0.73
    akespe
    -0.73
    Downloadha
    -0.72
    unal
    -0.68
    channelAvailability
    -0.67
    displayText
    -0.67
    animate
    -0.67
    POSITIVE LOGITS
     Productions
    1.62
     Studios
    1.45
     Brewing
    1.38
     Records
    1.31
     Brewery
    1.31
     Entertainment
    1.29
     Films
    1.25
     Pictures
    1.23
     Enterprises
    1.18
     Games
    1.16
    Activations Density 0.266%

    No Known Activations