© 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. 17339
    Prev
    Next
    INDEX
    Explanations

    words or phrases beginning with 'i'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize agreement or affirmation

    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
    iencies
    -0.69
    ocation
    -0.68
    gment
    -0.67
    LC
    -0.67
    tan
    -0.66
    tu
    -0.63
    unity
    -0.62
    ivities
    -0.62
    tur
    -0.61
    native
    -0.60
    POSITIVE LOGITS
     downright
    1.31
     quite
    1.01
     even
    0.99
     practically
    0.92
     virtually
    0.87
     almost
    0.87
     pretty
    0.86
     worse
    0.84
     EVEN
    0.81
     actually
    0.79
    Activations Density 0.228%

    No Known Activations