© 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. 7-RES-JB
    11. 1958
    Prev
    Next
    INDEX
    Explanations

    references to whistleblowers and the act of blowing the whistle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to whistleblowers and the act of blowing the whistle on a situation or wrongdoing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itating
    -0.73
    itates
    -0.73
    itals
    -0.71
    itated
    -0.69
    ists
    -0.67
    ter
    -0.66
    Urban
    -0.66
    ivan
    -0.66
    ggles
    -0.65
    Ļ½
    -0.65
    POSITIVE LOGITS
     whistle
    1.16
    dropping
    0.94
     whist
    0.84
    tower
    0.80
    vernment
    0.79
    keeper
    0.78
    sonian
    0.75
     sounded
    0.75
     whistlebl
    0.74
    backs
    0.74
    Activations Density 0.042%

    No Known Activations