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. 18072
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations, particularly Staten Island

    oai_token-act-pair · gpt-3.5-turbo

    references to Staten Island and its associated context

    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
    ioned
    -0.84
    hered
    -0.79
    kered
    -0.79
    cius
    -0.79
    riott
    -0.77
    ivia
    -0.76
    Leod
    -0.74
    wagen
    -0.72
    eners
    -0.72
    vP
    -0.72
    POSITIVE LOGITS
     borough
    1.13
     Borough
    1.10
     subway
    0.82
     Islanders
    0.81
     Armory
    0.77
     Staten
    0.76
     skyline
    0.74
     Island
    0.73
     Citiz
    0.73
     sidewalk
    0.73
    Activations Density 0.021%

    No Known Activations