© 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. 6-RES-JB
    11. 7784
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Japanese culture, especially names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly designers and creators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.78
     Scotia
    -0.76
    culosis
    -0.75
    istical
    -0.73
     handshake
    -0.71
    eering
    -0.70
    OPLE
    -0.70
    bably
    -0.66
    opsy
    -0.65
    istics
    -0.63
    POSITIVE LOGITS
    asaki
    1.04
    amoto
    0.94
    allows
    0.93
    esome
    0.91
    tower
    0.88
    athed
    0.84
    aii
    0.82
     GOODMAN
    0.82
    borgh
    0.82
    atsu
    0.80
    Activations Density 0.035%

    No Known Activations