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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 20495
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names like "Neil"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals named Neil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teen
    -0.70
    VALUE
    -0.70
     bearer
    -0.69
    holders
    -0.67
    pired
    -0.67
    escent
    -0.64
    itutes
    -0.64
     scant
    -0.63
    lishes
    -0.62
    itute
    -0.62
    POSITIVE LOGITS
     Gorsuch
    1.11
    son
    1.11
     Strauss
    0.91
     Armstrong
    0.86
     Patel
    0.83
    ordan
    0.82
     Fallon
    0.77
    thia
    0.77
    shire
    0.76
     Tyson
    0.76
    Activations Density 0.031%

    No Known Activations