© 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. 8-RES-JB
    11. 4221
    Prev
    Next
    INDEX
    Explanations

    names of people, especially the name "Evan."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Evan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lda
    -0.67
    ung
    -0.67
    inals
    -0.66
    esome
    -0.63
    tower
    -0.61
     insensitive
    -0.60
     reconc
    -0.59
    UV
    -0.59
     deduction
    -0.58
     coefficients
    -0.58
    POSITIVE LOGITS
     Spiegel
    0.95
    ston
    0.86
     Gree
    0.84
    odox
    0.82
    igans
    0.80
    rily
    0.75
    ildo
    0.75
    ufact
    0.75
    esc
    0.74
     Dunham
    0.73
    Activations Density 0.044%

    No Known Activations