© 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 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. 10-RES-JB
    11. 13150
    Prev
    Next
    INDEX
    Explanations

    names, particularly those with a strong focus on the letter combination "Ak"

    oai_token-act-pair · gpt-3.5-turbo

    references to names or terms related to weapons and notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruary
    -0.75
    enegger
    -0.71
    enhagen
    -0.65
    helle
    -0.62
    Reviewed
    -0.61
    issance
    -0.61
    lde
    -0.60
    emetery
    -0.60
    nesday
    -0.60
    kefeller
    -0.59
    POSITIVE LOGITS
    ļé
    0.72
    ļ
    0.70
    Pacific
    0.68
    Ĩ
    0.68
    umeric
    0.67
    «ĺ
    0.65
    ãĤ³
    0.63
    adi
    0.63
    ãĤ¦ãĤ¹
    0.63
    ccording
    0.62
    Activations Density 0.178%

    No Known Activations