© 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. 583
    Prev
    Next
    INDEX
    Explanations

    phrases related to names and identity

    oai_token-act-pair · gpt-3.5-turbo

    instances and references related to names and personal identification

    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
    alysis
    -0.86
    vable
    -0.83
    ractical
    -0.82
    grad
    -0.79
    issions
    -0.78
    edience
    -0.78
    grade
    -0.74
    alore
    -0.73
    merce
    -0.72
    monary
    -0.71
    POSITIVE LOGITS
     initials
    0.81
     nationality
    0.81
     suffix
    0.73
     Uzbek
    0.72
     ensu
    0.72
     Tup
    0.71
     Arabic
    0.70
     Whats
    0.69
     Hawaiian
    0.68
     nickname
    0.68
    Activations Density 0.456%

    No Known Activations