© 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. 6-RES-JB
    11. 2881
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal statements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and its variations in different contexts

    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
    sburg
    -0.83
     Quantity
    -0.78
    alus
    -0.74
     Spani
    -0.73
    know
    -0.71
    inav
    -0.68
    uld
    -0.66
    izons
    -0.65
    bury
    -0.64
    fields
    -0.64
    POSITIVE LOGITS
     unclear
    0.94
     also
    0.93
     widely
    0.91
     awarded
    0.90
     incon
    0.87
     unlikely
    0.86
     presented
    0.86
     billed
    0.86
     supposed
    0.85
     meant
    0.85
    Activations Density 0.316%

    No Known Activations