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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 7468
    Prev
    Next
    INDEX
    Explanations

    formal titles followed by a person's name with a last name starting with a capital letter

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals addressed as "Mr." alongside their titles or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phis
    -0.68
    ioch
    -0.67
    ashtra
    -0.65
    20439
    -0.63
     destro
    -0.62
    izu
    -0.62
    esa
    -0.62
    adas
    -0.61
     fallout
    -0.60
    ¥µ
    -0.60
    POSITIVE LOGITS
     Chairman
    1.37
     Speaker
    1.32
     President
    1.21
     Chair
    1.07
     PRESIDENT
    1.05
     Mayor
    1.03
    Chair
    1.03
     Secretary
    1.01
     Congressman
    0.95
     Chancellor
    0.95
    Activations Density 0.046%

    No Known Activations