© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14137
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to excess or exaggeration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "over" used in various contexts, indicating excessive or exaggerated situations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Dot
    -0.69
     Doe
    -0.69
    arium
    -0.66
     Lauder
    -0.66
    UES
    -0.65
     Salvation
    -0.63
    UE
    -0.61
     Gemini
    -0.61
     Walton
    -0.60
     Nirvana
    -0.60
    POSITIVE LOGITS
    priced
    1.22
    hang
    1.16
    blown
    1.11
    grown
    1.11
    stated
    1.10
    valued
    1.10
    kill
    1.10
    drive
    1.06
    confidence
    1.05
    lap
    1.04
    Activations Density 0.064%

    No Known Activations