© 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. 6-RES-JB
    11. 1516
    Prev
    Next
    INDEX
    Explanations

    words related to whistleblowing or the act of blowing a whistle as a signal

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "whistle" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggles
    -0.77
    itating
    -0.73
    ivan
    -0.73
    itates
    -0.71
    arov
    -0.69
    ists
    -0.68
    itate
    -0.68
    pite
    -0.65
    arya
    -0.65
    amins
    -0.65
    POSITIVE LOGITS
     whistle
    1.18
     whist
    1.07
    dropping
    0.99
    keeper
    0.95
     sounded
    0.84
    pipe
    0.83
     blew
    0.78
     blowing
    0.78
     blown
    0.78
    keepers
    0.77
    Activations Density 0.023%

    No Known Activations