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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20621
    Prev
    Next
    INDEX
    Explanations

    names of locations or people with a focus on Equatorial Guinea

    oai_token-act-pair · gpt-3.5-turbo

    geographical place names and their associations

    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
     Machina
    -0.79
     Cosponsors
    -0.76
    CHA
    -0.75
    REE
    -0.74
    externalActionCode
    -0.70
    IDA
    -0.69
    OME
    -0.69
    Lex
    -0.69
    æĦ
    -0.68
    ngth
    -0.68
    POSITIVE LOGITS
    adal
    1.01
    upe
    0.92
    ilitary
    0.91
    interstitial
    0.90
    ities
    0.85
    etric
    0.83
    ayan
    0.83
    orean
    0.83
    uxe
    0.82
    illac
    0.82
    Activations Density 0.013%

    No Known Activations