© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11742
    Prev
    Next
    INDEX
    Explanations

    mentions of whistleblowers

    oai_token-act-pair · gpt-3.5-turbo

    references to whistleblowers and whistleblowing activities

    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
    eele
    -0.81
    animate
    -0.80
    nis
    -0.73
     contiguous
    -0.72
    bris
    -0.72
    ustom
    -0.72
    zyme
    -0.71
    bal
    -0.71
    ross
    -0.69
    division
    -0.69
    POSITIVE LOGITS
     whistleblower
    0.96
     whistleblowers
    0.95
     whistlebl
    0.85
     testimonies
    0.82
     whistle
    0.79
     disclosures
    0.79
     revelations
    0.77
     informant
    0.77
    é¾įåĸļ士
    0.76
     extraord
    0.73
    Activations Density 0.014%

    No Known Activations