© 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. 1-RES-JB
    11. 3765
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "boy"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "boy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.91
    veyard
    -0.80
    andem
    -0.74
    odium
    -0.71
    adena
    -0.70
    inventoryQuantity
    -0.70
    reen
    -0.68
    insula
    -0.68
    tnc
    -0.67
     Elections
    -0.67
    POSITIVE LOGITS
    hood
    1.20
    boy
    1.14
     boy
    1.10
    boys
    1.10
    friend
    1.10
     Scouts
    1.00
     boys
    0.96
    ishly
    0.95
    Boy
    0.89
    cott
    0.86
    Activations Density 0.010%

    No Known Activations