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. 13027
    Prev
    Next
    INDEX
    Explanations

    words related to the city of Aurora, including locations, events, and community characteristics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Aurora" and its associated contexts or topics

    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
    eday
    -0.95
    hovah
    -0.89
    opher
    -0.86
    aps
    -0.85
    enegger
    -0.84
    etsu
    -0.84
    bered
    -0.83
    ophers
    -0.80
    erences
    -0.79
    oward
    -0.79
    POSITIVE LOGITS
     Bore
    1.20
     Austral
    0.93
     Aurora
    0.79
     Springs
    0.77
     Cannabis
    0.75
     Fem
    0.73
     Hazel
    0.72
     Centauri
    0.71
     Polaris
    0.70
     Valkyrie
    0.70
    Activations Density 0.018%

    No Known Activations