© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15021
    Prev
    Next
    INDEX
    Explanations

    mentions of the country 'Djibouti'

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Dj" or variations of it, likely indicating a focus on DJ culture or roles

    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
    imer
    -0.75
    Merit
    -0.70
    ear
    -0.66
    iegel
    -0.64
     auto
    -0.63
    ears
    -0.60
     steril
    -0.60
    omer
    -0.59
    IVES
    -0.59
    market
    -0.58
    POSITIVE LOGITS
     Dj
    4.29
     dj
    2.01
    dj
    1.98
     Django
    1.42
     Erit
    1.38
     Senegal
    1.33
     Bj
    1.26
    DJ
    1.26
     Dh
    1.25
     Dag
    1.22
    Activations Density 0.027%

    No Known Activations