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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 20780
    Prev
    Next
    INDEX
    Explanations

    mentions of the city name "Cincinnati" and possibly sports teams or related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Cincinnati and its associated sports teams or events

    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
    vana
    -0.86
    pring
    -0.80
    bes
    -0.77
    ledged
    -0.76
    iating
    -0.75
    ially
    -0.75
    eways
    -0.74
    lasses
    -0.73
    ariat
    -0.72
    inal
    -0.71
    POSITIVE LOGITS
     Bengals
    1.10
     Reds
    1.00
    incinn
    0.94
     Cincinnati
    0.88
    hurst
    0.78
    incinnati
    0.77
     Parks
    0.71
     Bengal
    0.70
     Zoo
    0.70
     Jail
    0.68
    Activations Density 0.013%

    No Known Activations