© 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 EvalsExportsinterp-engineNEWAPI 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. 5015
    Prev
    Next
    INDEX
    Explanations

    phrases related to paying attention to details or specific actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of paying attention or monetary payment

    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
     Archdemon
    -0.69
     Scotia
    -0.66
    ãĤ¬
    -0.65
    ember
    -0.65
    orically
    -0.64
    icity
    -0.63
    ierre
    -0.62
    _>
    -0.61
     Plain
    -0.61
    bum
    -0.61
    POSITIVE LOGITS
    checks
    0.97
     attention
    0.96
     heed
    0.94
     dues
    0.92
     dearly
    0.88
     homage
    0.88
    paying
    0.88
    loads
    0.86
     dividends
    0.81
     tribute
    0.80
    Activations Density 0.041%

    No Known Activations