© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10110
    Prev
    Next
    INDEX
    Explanations

    references to a specific sports team, "Lions", potentially relating to news, players, and games

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsius
    -0.90
    mble
    -0.90
     srf
    -0.89
     practition
    -0.89
    ntil
    -0.88
    lly
    -0.83
     Seym
    -0.83
    ccording
    -0.82
    aleigh
    -0.82
    DonaldTrump
    -0.79
    POSITIVE LOGITS
     Lions
    1.06
     Tigers
    0.89
    士
    0.79
     Pistons
    0.77
    dale
    0.75
    berger
    0.74
    izont
    0.73
     Packers
    0.72
    ergic
    0.72
    enium
    0.70
    Activations Density 0.006%

    No Known Activations