© 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. 4-RES-JB
    11. 7209
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual named "Castillo."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Castillo."

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

    No Comments

    Negative Logits
    race
    -0.78
    Ö¼
    -0.77
    rified
    -0.74
    icrobial
    -0.70
    Þ
    -0.69
    functional
    -0.69
    role
    -0.68
    schild
    -0.68
    sheet
    -0.67
    sonian
    -0.67
    POSITIVE LOGITS
     Gomez
    0.99
     Islands
    0.85
    illo
    0.83
     peppers
    0.81
     Toro
    0.81
    zzi
    0.76
    zar
    0.76
     Ortiz
    0.74
     Rico
    0.73
     Cruz
    0.72
    Activations Density 0.015%

    No Known Activations