© 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. 14485
    Prev
    Next
    INDEX
    Explanations

    comparisons or relationships related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating levels or increases in magnitude

    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
    ools
    -0.70
    ADRA
    -0.60
    ij士
    -0.58
    ĺħ
    -0.57
     SOFTWARE
    -0.55
    ritz
    -0.52
    Optional
    -0.52
     Wanted
    -0.52
    ĪĴ
    -0.51
    claimer
    -0.51
    POSITIVE LOGITS
     than
    1.23
     among
    1.10
    than
    1.06
    among
    1.02
     amongst
    1.00
     compared
    0.95
     across
    0.91
     nationally
    0.89
     Than
    0.88
     during
    0.84
    Activations Density 0.183%

    No Known Activations