© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    linguistic patterns related to language translation or analysis

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to cultural or social identity, particularly those with linguistic variation

    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
    nen
    -0.84
     Kardashian
    -0.70
    abad
    -0.67
    oway
    -0.66
     AAP
    -0.64
     Higgins
    -0.62
    ney
    -0.60
    bek
    -0.60
    sha
    -0.60
    pick
    -0.59
    POSITIVE LOGITS
    issance
    1.21
    uthor
    1.20
    hedral
    1.09
    ñ
    1.08
    isance
    1.06
    ç
    1.03
    ire
    1.03
    BILITIES
    1.03
    ires
    0.97
    BILITY
    0.95
    Activations Density 0.121%

    No Known Activations