© 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. 7-RES-JB
    11. 1912
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named Paul Nung, particularly focusing on his surname

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names, specifically those that begin with "Aung."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDER
    -0.73
    ãĥ¯ãĥ³
    -0.69
    Ò
    -0.68
    toe
    -0.68
    ãĥŀ
    -0.65
    Brexit
    -0.63
    Raven
    -0.63
    urity
    -0.62
    OME
    -0.62
    ERO
    -0.61
    POSITIVE LOGITS
    lasses
    1.24
    nir
    1.02
    oing
    0.97
    andr
    0.86
    ratulations
    0.86
    regate
    0.85
    undo
    0.81
    itives
    0.81
    sun
    0.80
    sung
    0.79
    Activations Density 0.026%

    No Known Activations