© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2937
    Prev
    Next
    INDEX
    Explanations

    locations or places, especially cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations or cities

    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
    rious
    -0.72
    eval
    -0.72
    acha
    -0.71
    big
    -0.69
    acter
    -0.69
    uchin
    -0.67
    chel
    -0.67
    leck
    -0.67
    lihood
    -0.66
    bler
    -0.65
    POSITIVE LOGITS
     PD
    0.77
     Pride
    0.75
     Tourism
    0.73
     City
    0.69
     citiz
    0.69
     GDP
    0.69
     Citiz
    0.69
     municipality
    0.67
     Directorate
    0.67
     newsp
    0.66
    Activations Density 0.491%

    No Known Activations