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. 6041
    Prev
    Next
    INDEX
    Explanations

    mentions of metropolitan areas

    oai_token-act-pair · gpt-3.5-turbo

    references to metropolitan areas or urban regions

    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
    arin
    -0.80
    icum
    -0.77
    oti
    -0.76
    roma
    -0.74
    Dialogue
    -0.71
    warm
    -0.69
    enf
    -0.68
    utan
    -0.68
    lain
    -0.68
    uth
    -0.68
    POSITIVE LOGITS
     metropolitan
    0.98
     area
    0.98
     tracts
    0.88
     metro
    0.83
     areas
    0.81
    ropolitan
    0.78
    plex
    0.76
    ãĥ³ãĤ¸
    0.74
     region
    0.72
     Atlanta
    0.71
    Activations Density 0.012%

    No Known Activations