© 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. 3-RES-JB
    11. 16910
    Prev
    Next
    INDEX
    Explanations

    are phrases related to sports statistics and activities

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in sports statistics or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scatter
    -0.77
     bureaucracy
    -0.70
     monop
    -0.67
     dispers
    -0.67
     bureaucratic
    -0.65
     scattering
    -0.65
     guiActiveUnfocused
    -0.64
     Romanian
    -0.64
     bureaucr
    -0.63
     drown
    -0.63
    POSITIVE LOGITS
    ¹
    0.92
    acca
    0.84
    ı
    0.80
    Miami
    0.78
    £
    0.77
    ï¸ı
    0.76
    mental
    0.75
    ¢
    0.75
    ulty
    0.74
    Los
    0.74
    Activations Density 0.616%

    No Known Activations