© 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. 1-RES-JB
    6. 20289
    Prev
    Next
    INDEX
    Explanations

    references to football positions, specifically "receiver"

    oai_token-act-pair · gpt-3.5-turbo

    references to football positions, specifically wide receivers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urb
    -0.75
    sis
    -0.73
    ename
    -0.68
    eking
    -0.67
    âĸĪâĸĪ
    -0.63
    vg
    -0.61
    uman
    -0.61
    udic
    -0.61
    zai
    -0.61
    upid
    -0.60
    POSITIVE LOGITS
     Receiver
    1.31
     receiver
    1.25
     receivers
    1.16
    ceiver
    0.89
     Rece
    0.89
     pige
    0.84
     transmitter
    0.79
    miah
    0.78
    backer
    0.75
     antennas
    0.74
    Activations Density 0.007%

    No Known Activations