© 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. 15570
    Prev
    Next
    INDEX
    Explanations

    names starting with "Wanda"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Anda" or variations of it within the text

    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
    sed
    -0.90
    icka
    -0.75
    paio
    -0.72
    lav
    -0.71
     deriv
    -0.71
    bard
    -0.70
    alcohol
    -0.69
    dn
    -0.66
    cffff
    -0.66
    alties
    -0.66
    POSITIVE LOGITS
    emonium
    1.25
     Devi
    0.94
    ibo
    0.87
     Haram
    0.84
    isance
    0.81
    wana
    0.79
    ignt
    0.78
    ju
    0.77
    arov
    0.77
    esque
    0.72
    Activations Density 0.012%

    No Known Activations