© 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. 4-RES-JB
    11. 20806
    Prev
    Next
    INDEX
    Explanations

    the word "know" as a primary trigger

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.84
    phrine
    -0.83
    otom
    -0.82
    uckland
    -0.82
    gdala
    -0.82
     sidx
    -0.77
    gencies
    -0.75
    ĪĴ
    -0.74
    ickr
    -0.73
    coni
    -0.73
    POSITIVE LOGITS
     anymore
    1.01
     yet
    0.80
     how
    0.80
     anything
    0.79
     nor
    0.74
    yet
    0.71
    ledged
    0.68
    lege
    0.67
     exactly
    0.67
     until
    0.67
    Activations Density 0.043%

    No Known Activations