© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3408
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns with a specific letter pattern

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the letter 'h'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.72
     Clause
    -0.70
    é¾įå¥ij士
    -0.61
     Kush
    -0.61
     Weeks
    -0.59
     Everywhere
    -0.59
    terday
    -0.57
     heartbeat
    -0.57
     Bigfoot
    -0.57
     First
    -0.56
    POSITIVE LOGITS
    Ãī
    0.91
    vor
    0.88
    oys
    0.86
    aus
    0.83
    acia
    0.82
    arten
    0.79
    alt
    0.78
    och
    0.78
    uit
    0.76
    ttp
    0.76
    Activations Density 0.031%

    No Known Activations