© 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. 1-RES-JB
    11. 20630
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically surnames

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals associated with legal or immigration contexts, particularly the name "Gonzalez."

    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
    umbn
    -0.89
    cess
    -0.79
    ãĥĦ
    -0.76
    inent
    -0.74
    published
    -0.70
    otions
    -0.70
    angible
    -0.69
    enment
    -0.69
    utive
    -0.69
    ãĥł
    -0.69
    POSITIVE LOGITS
     Gonzalez
    1.25
    alez
    1.01
     Alonso
    0.87
     Gutierrez
    0.77
     corrid
    0.76
     Cabrera
    0.75
     lapt
    0.75
     Ramos
    0.75
    SHIP
    0.75
    arella
    0.74
    Activations Density 0.011%

    No Known Activations