© 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. 9-RES-JB
    11. 10358
    Prev
    Next
    INDEX
    Explanations

    terms related to names or titles including 'n'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "n" and variations of the word "rock."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¿½
    -0.77
    sole
    -0.74
    ansk
    -0.72
    cfg
    -0.70
    GMT
    -0.68
    wordpress
    -0.67
    mand
    -0.66
    central
    -0.65
    COM
    -0.65
    idian
    -0.64
    POSITIVE LOGITS
     Roses
    0.84
     Packs
    0.81
    '-
    0.73
     Frog
    0.72
    ocker
    0.72
    abbit
    0.71
    ighters
    0.69
     Wrestling
    0.69
     Wolves
    0.67
     Shake
    0.66
    Activations Density 0.162%

    No Known Activations