© 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. 8-RES-JB
    11. 6486
    Prev
    Next
    INDEX
    Explanations

    phrases related to whistleblowing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "whistle" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itates
    -0.82
    itating
    -0.74
    itate
    -0.71
    itated
    -0.71
    rators
    -0.70
     Conquest
    -0.70
    rator
    -0.70
    Ļ½
    -0.68
    izable
    -0.67
    ggles
    -0.66
    POSITIVE LOGITS
     whistle
    1.16
    dropping
    1.03
    keeper
    0.87
     whist
    0.87
    vernment
    0.76
     blowing
    0.76
     sounded
    0.75
    grass
    0.75
     blown
    0.75
    cone
    0.75
    Activations Density 0.057%

    No Known Activations