© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    locations or geographical entities

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

    proper nouns related to geographic locations and organizations

    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
    Oracle
    -0.86
    hedon
    -0.68
    haw
    -0.68
    nob
    -0.67
    elman
    -0.65
    inventoryQuantity
    -0.64
     Nanto
    -0.63
    crow
    -0.61
     Genie
    -0.60
    indu
    -0.60
    POSITIVE LOGITS
     Ltd
    1.16
     LLC
    0.93
     Limited
    0.85
     affiliate
    0.83
     Partnership
    0.82
     Chapter
    0.80
     headquarters
    0.80
     Headquarters
    0.79
     Edition
    0.78
     Region
    0.78
    Activations Density 0.217%

    No Known Activations