© 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. 2-RES-JB
    11. 18285
    Prev
    Next
    INDEX
    Explanations

    the term "Wings" when associated with sports teams, specifically the Detroit Red Wings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Detroit Red Wings hockey team

    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
     McA
    -0.66
    anyahu
    -0.64
    balance
    -0.64
    SPONSORED
    -0.63
    ALLY
    -0.62
     Aber
    -0.62
    adal
    -0.62
    ãĥª
    -0.60
     sher
    -0.60
    天
    -0.59
    POSITIVE LOGITS
     Wings
    1.27
    wings
    1.08
    pan
    1.00
    nuts
    0.92
    pread
    0.88
    layer
    0.85
    warm
    0.83
    fan
    0.81
    ski
    0.80
     Pistons
    0.80
    Activations Density 0.011%

    No Known Activations