© 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. 2-RES-JB
    11. 22120
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Neil."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Neil."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VALUE
    -0.84
     bearer
    -0.78
    cffff
    -0.74
    Ranked
    -0.74
    ensed
    -0.73
    DragonMagazine
    -0.73
    EStreamFrame
    -0.71
    tnc
    -0.67
    esthetic
    -0.67
    76561
    -0.65
    POSITIVE LOGITS
     Neil
    1.18
     Gorsuch
    1.07
     Armstrong
    0.98
    Neil
    0.95
     Tyson
    0.91
    aiman
    0.88
     Craig
    0.88
     Fallon
    0.88
     Adams
    0.84
     Strauss
    0.84
    Activations Density 0.004%

    No Known Activations