© 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. 11-RES-JB
    11. 15706
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and standings

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.77
     VICE
    -0.74
     AFP
    -0.72
     ESA
    -0.71
    EVA
    -0.71
     UNESCO
    -0.69
     Vanity
    -0.69
    SPONSORED
    -0.66
     Shutterstock
    -0.66
     relativity
    -0.66
    POSITIVE LOGITS
    hawks
    1.17
    agles
    1.11
    seys
    1.09
    awks
    1.07
    wolves
    1.07
    igers
    1.07
    orns
    1.07
    runners
    1.07
    Stars
    1.05
    cats
    1.05
    Activations Density 0.169%

    No Known Activations