© 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. 2-RES-JB
    11. 21637
    Prev
    Next
    INDEX
    Explanations

    words related to the position of "linebacker" in American football

    oai_token-act-pair · gpt-3.5-turbo

    references to linebackers in football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emb
    -0.76
    apest
    -0.75
    oric
    -0.73
    orative
    -0.72
    ora
    -0.70
    atom
    -0.69
    iences
    -0.67
    okers
    -0.67
    ebus
    -0.67
    ointment
    -0.67
    POSITIVE LOGITS
     linebacker
    1.13
    backer
    1.00
     cornerback
    0.84
     linebackers
    0.83
     lineman
    0.78
     lineback
    0.77
     outfielder
    0.75
     clad
    0.72
     pads
    0.69
     infield
    0.69
    Activations Density 0.014%

    No Known Activations