© 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. 0-RES-JB
    11. 19894
    Prev
    Next
    INDEX
    Explanations

    references or mentions of the word "Columbia."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Columbia," particularly in various contexts related to places or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lapt
    -0.78
    uous
    -0.77
    ADRA
    -0.75
    ef
    -0.67
    efer
    -0.66
    weak
    -0.65
     worsh
    -0.65
    á
    -0.64
    attribute
    -0.64
     ts
    -0.62
    POSITIVE LOGITS
     Columbia
    4.03
    Columb
    2.35
     Columb
    2.14
     Colombia
    1.37
     Georgetown
    1.33
     Princeton
    1.29
     Yale
    1.25
     Charleston
    1.19
     Concord
    1.18
     NYU
    1.17
    Activations Density 0.025%

    No Known Activations