© 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. 19973
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures or events

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and names, particularly related to geography, politics, or organizations

    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
    ãĥ¼ãĥĨ
    -0.75
    ãĥł
    -0.70
    erto
    -0.67
    rency
    -0.62
     Collider
    -0.62
    BILITIES
    -0.62
    eele
    -0.61
     epid
    -0.61
    ãĥĥãĥĪ
    -0.60
    enment
    -0.60
    POSITIVE LOGITS
    akov
    0.81
    abytes
    0.75
    oslav
    0.74
    terday
    0.73
    ovych
    0.71
    udi
    0.69
     reckoning
    0.67
    aston
    0.65
    awa
    0.63
    kees
    0.63
    Activations Density 0.141%

    No Known Activations