© 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. 6-RES-JB
    11. 5635
    Prev
    Next
    INDEX
    Explanations

    proper nouns like "Randy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Randy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strings
    -0.88
    ivity
    -0.81
    ioch
    -0.78
    ivism
    -0.77
    oresc
    -0.75
    orescence
    -0.75
    ences
    -0.73
    orescent
    -0.72
    ogens
    -0.70
    unction
    -0.68
    POSITIVE LOGITS
     Cout
    0.91
    wine
    0.87
     Olson
    0.82
     Savage
    0.79
    vich
    0.78
    croft
    0.78
     Castle
    0.75
     Bauer
    0.73
     Ples
    0.71
     Hendricks
    0.70
    Activations Density 0.022%

    No Known Activations