© 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. 6696
    Prev
    Next
    INDEX
    Explanations

    statements of knowledge or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express knowledge or certainty about various topics

    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
     me
    -0.77
    attery
    -0.61
    ĪĴ
    -0.61
    onies
    -0.60
    ashing
    -0.60
    onial
    -0.60
    inance
    -0.59
    my
    -0.59
    rentice
    -0.59
    phant
    -0.58
    POSITIVE LOGITS
     anecd
    1.07
     ourselves
    0.89
     from
    0.72
     that
    0.71
     about
    0.70
     definitively
    0.65
     how
    0.62
     unequivocally
    0.61
     plenty
    0.61
     instinctively
    0.60
    Activations Density 0.122%

    No Known Activations