© 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. 16638
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly names or initials of notable people

    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
    theless
    -0.81
    minecraft
    -0.65
     FTA
    -0.59
     IPS
    -0.58
    falls
    -0.57
    itness
    -0.57
     retake
    -0.57
    wl
    -0.56
    heid
    -0.55
     âĸĪ
    -0.55
    POSITIVE LOGITS
     Gaal
    0.92
    pez
    0.72
    bourg
    0.70
    vez
    0.69
    uel
    0.67
    iao
    0.64
     Gaul
    0.63
    amph
    0.63
    leon
    0.61
    Benz
    0.60
    Activations Density 0.108%

    No Known Activations