© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1869
    Prev
    Next
    INDEX
    Explanations

    negative statements or refusals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or negativity

    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
    éŃĶ
    -0.78
    éĹĺ
    -0.77
    *:
    -0.72
    è¦ļéĨĴ
    -0.72
    ãģ®ç
    -0.70
     duly
    -0.70
    iberal
    -0.69
    ailability
    -0.67
    姫
    -0.66
    ãĥIJ
    -0.66
    POSITIVE LOGITS
     necessarily
    1.05
     flashy
    1.00
     anybody
    0.95
     anymore
    0.91
     disrespect
    0.90
     [
    0.88
     scrim
    0.87
     anything
    0.83
     gonna
    0.83
     compromising
    0.83
    Activations Density 0.250%

    No Known Activations