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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16494
    Prev
    Next
    INDEX
    Explanations

    names of individuals or families

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of families and prominent individuals

    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
    olulu
    -0.85
    ASHINGTON
    -0.60
     Nasa
    -0.59
    iversal
    -0.58
    iguous
    -0.58
    llor
    -0.57
    MW
    -0.57
    BU
    -0.57
     Javier
    -0.56
    enser
    -0.56
    POSITIVE LOGITS
     brothers
    1.25
     family
    1.12
     Brothers
    1.07
     sisters
    1.06
     twins
    1.04
     clan
    1.02
     Effect
    0.98
     affair
    0.95
     household
    0.91
     Family
    0.90
    Activations Density 0.190%

    No Known Activations