© 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. 3-RES-JB
    11. 705
    Prev
    Next
    INDEX
    Explanations

    references to specific sports teams, particularly the Atlanta Falcons and the Atlanta Braves

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams, particularly the Atlanta Falcons and Braves

    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
    lying
    -0.73
     Kardashian
    -0.69
    ocard
    -0.67
     srfAttach
    -0.66
     Niet
    -0.65
    pert
    -0.65
     Cao
    -0.63
    zanne
    -0.63
     dele
    -0.62
    tics
    -0.61
    POSITIVE LOGITS
     Falcons
    1.22
     Braves
    0.91
    layer
    0.82
    daq
    0.82
     Buccaneers
    0.81
     Hawks
    0.78
    ipeg
    0.78
    ï¸
    0.77
    BSD
    0.77
    Vision
    0.69
    Activations Density 0.011%

    No Known Activations