© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18610
    Prev
    Next
    INDEX
    Explanations

    references to locations, specifically the city of Kansas City

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Kansas City."

    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
    icides
    -0.91
    rity
    -0.80
    arial
    -0.76
    icide
    -0.75
    wcsstore
    -0.75
    orescence
    -0.74
    itive
    -0.73
    ances
    -0.73
    iotic
    -0.73
    oresc
    -0.72
    POSITIVE LOGITS
    scape
    0.98
     skyline
    0.87
     Council
    0.81
     metro
    0.80
     Islanders
    0.79
     Marathon
    0.77
     Limits
    0.76
     Heights
    0.75
     suburb
    0.75
     FC
    0.73
    Activations Density 0.027%

    No Known Activations