© 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. 0-RES-JB
    11. 10462
    Prev
    Next
    INDEX
    Explanations

    terms related to American football positions, particularly the position of wide receiver

    oai_token-act-pair · gpt-3.5-turbo

    references to wide receivers in football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Asians
    -0.71
    mins
    -0.68
     Gum
    -0.65
     Um
    -0.65
    neys
    -0.64
     Panda
    -0.63
    nces
    -0.63
    enges
    -0.63
    Myth
    -0.62
     Il
    -0.62
    POSITIVE LOGITS
     receiver
    3.80
     receivers
    3.14
     Receiver
    2.99
     transmitter
    1.74
    ceiver
    1.65
     cornerback
    1.62
     Rece
    1.51
     sender
    1.41
     linebacker
    1.35
     quarterback
    1.28
    Activations Density 0.018%

    No Known Activations