© 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. 13643
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Cleveland" in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the substring "Cle" or variations of it

    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
     Galaxy
    -0.65
     numbered
    -0.58
     950
    -0.58
     gag
    -0.57
     Bravo
    -0.57
     provoking
    -0.56
    BLE
    -0.56
     disparate
    -0.55
    NOW
    -0.55
     Kling
    -0.54
    POSITIVE LOGITS
    avage
    1.32
    arest
    1.31
    veland
    1.28
    mson
    1.24
    aver
    1.14
    mens
    1.11
    combe
    1.11
    vern
    1.11
    arer
    1.09
    mons
    1.02
    Activations Density 0.027%

    No Known Activations