© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21841
    Prev
    Next
    INDEX
    Explanations

    references to sporting events or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "at" in temporal or locational contexts

    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
    hops
    -0.85
    jri
    -0.75
    hop
    -0.74
    vous
    -0.73
    SPONSORED
    -0.73
    bender
    -0.71
    iscal
    -0.69
    ranged
    -0.69
    ources
    -0.69
     ceilings
    -0.68
    POSITIVE LOGITS
     Soldier
    1.17
     Stub
    1.14
     Wembley
    1.12
     Fen
    1.10
     Staples
    1.09
     Yankee
    1.08
     Hof
    1.04
     Century
    1.04
     Qualcomm
    1.04
     FedEx
    1.02
    Activations Density 0.086%

    No Known Activations