© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and opposition

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    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
    olves
    -0.73
    ãģł
    -0.66
    umen
    -0.65
    çļ
    -0.65
    ¬¼
    -0.64
    atro
    -0.62
    ===
    -0.61
    =-=-=-=-=-=-=-=-
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    combe
    -0.60
    POSITIVE LOGITS
     fearing
    1.32
     saying
    1.31
     arguing
    1.30
     believing
    1.28
     noting
    1.24
     preferring
    1.22
     citing
    1.17
     insisting
    1.15
     claiming
    1.15
     which
    1.12
    Activations Density 0.269%

    No Known Activations