© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 6516
    Prev
    Next
    INDEX
    Explanations

    words related to an American football team named "Lions."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Detroit Lions football team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.98
    elsius
    -0.93
    ntil
    -0.93
    lly
    -0.88
     Seym
    -0.87
     srf
    -0.86
    ccording
    -0.86
    cknow
    -0.82
    DonaldTrump
    -0.81
     practition
    -0.78
    POSITIVE LOGITS
     Lions
    1.26
     Tigers
    0.97
     Pistons
    0.84
     Wings
    0.79
     Packers
    0.78
     Clubs
    0.75
     Vikings
    0.74
     Tracks
    0.73
     Blazers
    0.71
    burg
    0.70
    Activations Density 0.005%

    No Known Activations