© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12014
    Prev
    Next
    INDEX
    Explanations

    instances of player transactions in sports, particularly involving releases

    oai_token-act-pair · gpt-3.5-turbo

    references to player releases and transactions in sports contexts

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

    No Comments

    Negative Logits
     Forth
    -0.81
    mb
    -0.80
    pes
    -0.77
    ymm
    -0.75
    gom
    -0.74
    organ
    -0.74
     Towards
    -0.69
    warts
    -0.69
    rpm
    -0.68
     Sector
    -0.67
    POSITIVE LOGITS
     offseason
    0.99
     jerseys
    0.98
    ESPN
    0.98
     waivers
    0.97
    juries
    0.94
    jured
    0.92
    NFL
    0.90
     undrafted
    0.89
     signings
    0.88
    jury
    0.88
    Activations Density 0.266%

    No Known Activations