© 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. 7993
    Prev
    Next
    INDEX
    Explanations

    words related to sports transactions (such as trading, acquiring, dealing, and picks)

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to sports trades and player transactions

    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
    tips
    -0.82
    nec
    -0.82
    tests
    -0.80
    aminer
    -0.80
    Sym
    -0.77
    Test
    -0.76
    Witness
    -0.75
    HUD
    -0.73
    nah
    -0.72
    Critical
    -0.71
    POSITIVE LOGITS
     retaining
    0.90
     cheaply
    0.83
     âĤ¬
    0.80
     USD
    0.74
     retain
    0.70
     £
    0.69
     conditional
    0.69
     bargain
    0.69
    igslist
    0.68
     bankrupt
    0.68
    Activations Density 0.285%

    No Known Activations