© 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. 3-RES-JB
    11. 22594
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific individuals or locations, with a focus on names like "Szeklers", "Rwanda", and "Nathaniel"

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to specific individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    things
    -0.77
    ¥µ
    -0.73
    viol
    -0.72
    wcs
    -0.71
     pengu
    -0.71
    handled
    -0.70
     surg
    -0.67
    oys
    -0.66
     genders
    -0.65
    icy
    -0.65
    POSITIVE LOGITS
     Monarch
    0.88
    ystem
    0.86
    iewicz
    0.83
     Sz
    0.77
     Vengeance
    0.74
    ombie
    0.73
    assian
    0.72
    hift
    0.72
    ynthesis
    0.72
    asper
    0.71
    Activations Density 0.033%

    No Known Activations