© 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. 8-RES-JB
    11. 17751
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, particularly the team name "Saints"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Saints and Southampton football teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ihad
    -0.84
    ators
    -0.80
    acan
    -0.79
    pour
    -0.79
    opsy
    -0.78
    ated
    -0.77
    agy
    -0.76
    berman
    -0.75
    iary
    -0.74
    Enlarge
    -0.74
    POSITIVE LOGITS
     Yard
    1.00
     Saints
    0.94
     Row
    0.71
     Parish
    0.70
     Cathedral
    0.68
    crow
    0.67
    mington
    0.65
     Presbyter
    0.63
     lineback
    0.63
     Bounty
    0.61
    Activations Density 0.063%

    No Known Activations