© 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. 12084
    Prev
    Next
    INDEX
    Explanations

    phrases related to significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    statements about resilience and overcoming challenges

    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
     Previously
    -0.76
    soDeliveryDate
    -0.72
    Later
    -0.71
    Secondly
    -0.70
    ļéĨĴ
    -0.69
     Later
    -0.68
    ago
    -0.68
    rin
    -0.68
     earlier
    -0.68
     secondly
    -0.67
    POSITIVE LOGITS
     ALWAYS
    1.23
     whichever
    1.11
     invariably
    1.06
     always
    1.03
     boils
    0.91
    always
    0.81
     anytime
    0.80
    ichever
    0.79
     wherever
    0.78
     regardless
    0.77
    Activations Density 0.408%

    No Known Activations