© 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. 9-RES-JB
    11. 10201
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "took."

    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
    è¦ļéĨĴ
    -0.70
    cape
    -0.69
     constitu
    -0.63
    Cong
    -0.61
     Smile
    -0.61
    lex
    -0.61
    gom
    -0.60
    rehens
    -0.59
    lite
    -0.59
    idding
    -0.59
    POSITIVE LOGITS
     advantage
    1.18
     aback
    1.16
     pains
    1.09
     refuge
    1.03
    aways
    0.91
     exception
    0.88
     heed
    0.86
     precautions
    0.85
     aim
    0.83
     liberties
    0.82
    Activations Density 0.078%

    No Known Activations