© 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. 7-RES-JB
    11. 18692
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the Monica Lewinsky scandal

    oai_token-act-pair · gpt-3.5-turbo

    multiple references to the name "Lew" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ACTED
    -0.90
    CHR
    -0.77
     à¨
    -0.75
    expr
    -0.73
    ¥µ
    -0.71
    thood
    -0.66
    ++++++++++++++++
    -0.65
    NetMessage
    -0.63
    Asia
    -0.63
     bulls
    -0.62
    POSITIVE LOGITS
    andowski
    1.49
    insky
    1.15
    inski
    0.94
    enstein
    0.92
    erk
    0.84
    ington
    0.83
    ont
    0.81
     Lew
    0.81
    iky
    0.80
    etz
    0.80
    Activations Density 0.036%

    No Known Activations