© 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. 3-RES-JB
    11. 14773
    Prev
    Next
    INDEX
    Explanations

    words related to the country "Jordan."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Jordan" and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forms
    -0.82
     accur
    -0.75
     ancest
    -0.73
     midterm
    -0.70
     predictive
    -0.70
    mble
    -0.66
     explan
    -0.66
    raviolet
    -0.65
    eding
    -0.65
    erest
    -0.65
    POSITIVE LOGITS
    oglu
    1.14
     Jordanian
    1.06
     Jordan
    1.04
    Jordan
    1.00
     Airways
    0.85
    ican
    0.81
     Arabian
    0.79
    phal
    0.79
     Turk
    0.78
    pora
    0.77
    Activations Density 0.004%

    No Known Activations