© 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. 21101
    Prev
    Next
    INDEX
    Explanations

    sentences containing unusual characters, such as "Ċ", "âĢ", and "ľ"

    oai_token-act-pair · gpt-3.5-turbo

    references to communication or written correspondence

    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
     redes
    -0.88
     ende
    -0.84
     earthqu
    -0.84
     neighb
    -0.82
     unbeliev
    -0.75
     nodd
    -0.75
     rul
    -0.74
     destro
    -0.73
     confir
    -0.72
     Keystone
    -0.71
    POSITIVE LOGITS
    "âĢ¦
    1.88
    "[
    1.81
    "...
    1.74
    "'
    1.74
    Quote
    1.57
    Dear
    1.55
    "
    1.55
    "(
    1.48
    "-
    1.42
    advertising
    1.41
    Activations Density 0.150%

    No Known Activations