© 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. 10329
    Prev
    Next
    INDEX
    Explanations

    names, especially those with a repeated letter in the middle

    oai_token-act-pair · gpt-3.5-turbo

    the name "John" in various contexts

    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
     awoken
    -0.65
     tongues
    -0.61
     Panther
    -0.59
     seams
    -0.59
     ABE
    -0.59
     Reborn
    -0.57
    ngth
    -0.57
    utor
    -0.57
    Fal
    -0.57
     Hurricanes
    -0.57
    POSITIVE LOGITS
    awk
    1.21
    ttp
    1.13
    olics
    1.10
    tml
    1.09
    awks
    1.05
    oho
    0.96
    undred
    0.96
    ansen
    0.94
    ickey
    0.94
    ospital
    0.92
    Activations Density 0.030%

    No Known Activations