© 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. 2-RES-JB
    11. 17612
    Prev
    Next
    INDEX
    Explanations

    words related to whistleblowers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    animate
    -0.78
    pop
    -0.77
    eon
    -0.77
    anus
    -0.76
    laus
    -0.75
    otropic
    -0.73
    eb
    -0.73
    eele
    -0.72
    aple
    -0.70
    bal
    -0.70
    POSITIVE LOGITS
     whistleblower
    1.12
     whistleblowers
    1.06
     whistlebl
    0.91
     disclosures
    0.89
     whistle
    0.84
    é¾įåĸļ士
    0.80
     revelations
    0.78
     informant
    0.78
     acknowled
    0.77
     briefings
    0.76
    Activations Density 0.015%

    No Known Activations