© 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. 4-RES-JB
    11. 10178
    Prev
    Next
    INDEX
    Explanations

    phrases related to cities, particularly Kansas City

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "City" with various associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eline
    -0.77
    ivia
    -0.75
    wcsstore
    -0.74
    arial
    -0.74
    syn
    -0.72
    uckland
    -0.71
    riet
    -0.71
    letcher
    -0.71
     showc
    -0.70
    idel
    -0.70
    POSITIVE LOGITS
     Chiefs
    0.95
    scape
    0.89
     Council
    0.85
     Heights
    0.78
     Limits
    0.71
     mayors
    0.71
     Lumpur
    0.70
     City
    0.70
     Mayor
    0.69
     Athletic
    0.68
    Activations Density 0.018%

    No Known Activations