© 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. 544
    Prev
    Next
    INDEX
    Explanations

    the proper noun "Carney"

    oai_token-act-pair · gpt-4-turbo

    the name 'Carney'

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Carney."

    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
    Ĥ¬
    -0.86
    Ñĭ
    -0.77
    оÐ
    -0.73
    ÑĮ
    -0.72
    ership
    -0.71
    ablishment
    -0.71
    sch
    -0.70
     Antar
    -0.70
    ĺħ
    -0.70
    matic
    -0.69
    POSITIVE LOGITS
     Carney
    0.98
     vetoed
    0.80
     blockade
    0.76
    ascus
    0.69
     calmed
    0.68
     blush
    0.67
    acas
    0.66
     hump
    0.66
     sleeves
    0.65
    ucci
    0.65
    Activations Density 0.005%

    No Known Activations