© 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. 2-RES-JB
    11. 9095
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Eleven"

    oai_token-act-pair · gpt-3.5-turbo

    references to the number eleven

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.89
     Kenobi
    -0.84
    sburgh
    -0.82
     Kers
    -0.74
    DERR
    -0.74
     Papers
    -0.73
    lace
    -0.71
     Fargo
    -0.70
     Kislyak
    -0.68
     Keane
    -0.67
    POSITIVE LOGITS
    venth
    1.38
    phant
    1.18
    ven
    0.89
    ele
    0.88
    LECT
    0.86
    fter
    0.84
    Ele
    0.83
    oton
    0.81
    teenth
    0.78
    YS
    0.78
    Activations Density 0.014%

    No Known Activations