Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19251
    Prev
    Next
    INDEX
    Explanations

    mentions of the sports team "Detroit Red Wings"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Wings," specifically in relation to 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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anyahu
    -0.89
    yss
    -0.74
    ctica
    -0.73
    izabeth
    -0.66
    abin
    -0.64
    ouple
    -0.63
    autical
    -0.63
    uments
    -0.63
    tery
    -0.62
    acci
    -0.62
    POSITIVE LOGITS
     Wings
    0.95
    hip
    0.84
    pan
    0.82
    pread
    0.77
    layer
    0.75
     Tigers
    0.73
     maiden
    0.73
    ski
    0.73
    warm
    0.72
    nuts
    0.71
    Activations Density 0.021%

    No Known Activations