© 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. 2-RES-JB
    11. 12615
    Prev
    Next
    INDEX
    Explanations

    references to a person named Terry

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Terry"

    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
    ĺħ
    -0.87
    xual
    -0.83
    artifacts
    -0.75
    ously
    -0.73
    76561
    -0.71
    ktop
    -0.68
    uckland
    -0.67
    ntil
    -0.67
    olate
    -0.65
    joined
    -0.64
    POSITIVE LOGITS
     Terry
    1.10
     McAuliffe
    0.95
    Terry
    0.90
     Richardson
    0.88
     Allen
    0.85
     McCorm
    0.84
     McA
    0.83
     Bran
    0.82
     Williams
    0.80
     Collins
    0.80
    Activations Density 0.012%

    No Known Activations