© 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. 3946
    Prev
    Next
    INDEX
    Explanations

    references to the country Uganda

    oai_token-act-pair · gpt-3.5-turbo

    references to Uganda

    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
    pard
    -0.81
    alty
    -0.80
    perature
    -0.79
    uters
    -0.77
    âĸ¬
    -0.67
    hent
    -0.66
    voy
    -0.65
    ocular
    -0.65
    place
    -0.65
    utenant
    -0.65
    POSITIVE LOGITS
    andan
    1.38
     Ug
    1.14
     Uganda
    1.02
    rica
    0.91
     Haram
    0.89
     Erit
    0.85
     Zamb
    0.81
    istani
    0.80
     Rw
    0.77
    rican
    0.77
    Activations Density 0.011%

    No Known Activations