© 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. 1-RES-JB
    11. 16786
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically cities

    oai_token-act-pair · gpt-3.5-turbo

    references to cities, particularly focusing on the word "city" itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arios
    -0.99
    igham
    -0.96
    etsk
    -0.95
    én
    -0.85
    dates
    -0.85
    ibaba
    -0.85
    ules
    -0.81
    yip
    -0.80
    reditary
    -0.79
    sembly
    -0.78
    POSITIVE LOGITS
    scape
    1.16
     skyline
    1.04
    wide
    0.98
     councillor
    0.96
     council
    0.94
     mayor
    0.91
     hall
    0.91
     ordinance
    0.88
     mayors
    0.86
     streets
    0.85
    Activations Density 0.034%

    No Known Activations