© 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. 2-RES-JB
    11. 4365
    Prev
    Next
    INDEX
    Explanations

    proper nouns of countries or locations

    oai_token-act-pair · gpt-3.5-turbo

    the name of a specific country

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fasc
    -0.68
     qualified
    -0.68
     vol
    -0.66
     min
    -0.61
    sectional
    -0.61
    rawdownloadcloneembedreportprint
    -0.60
     plural
    -0.60
     sound
    -0.60
     maximal
    -0.60
     cis
    -0.59
    POSITIVE LOGITS
    etsk
    0.94
    cles
    0.77
    ansk
    0.77
    hend
    0.76
    ennes
    0.73
    isf
    0.73
    wcsstore
    0.73
    asus
    0.73
    ames
    0.72
    rive
    0.71
    Activations Density 0.000%

    No Known Activations