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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17283
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and their associated cities

    oai_token-act-pair · gpt-3.5-turbo

    references to the Calgary Flames hockey team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agers
    -0.86
    aceae
    -0.81
    ager
    -0.80
    iary
    -0.77
    eanor
    -0.76
    icals
    -0.76
    iaries
    -0.76
    abet
    -0.76
    ively
    -0.75
    orship
    -0.75
    POSITIVE LOGITS
     Flames
    1.04
     Lumpur
    0.78
    Tex
    0.75
    Cow
    0.70
     Calgary
    0.69
    ®
    0.69
     Springs
    0.68
    emin
    0.67
     Herald
    0.67
     Lions
    0.66
    Activations Density 0.039%

    No Known Activations