© 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. 10-RES-JB
    11. 18573
    Prev
    Next
    INDEX
    Explanations

    mentions of events, conferences, meetings, conventions, and gatherings

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or gatherings

    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
     lied
    -0.77
    cells
    -0.75
     survives
    -0.74
     denies
    -0.72
    sheets
    -0.71
     existed
    -0.71
    qus
    -0.69
    arre
    -0.69
    Layer
    -0.69
    mares
    -0.69
    POSITIVE LOGITS
     annual
    1.27
     inaugural
    1.23
     unveiling
    1.22
     inauguration
    1.20
     festivities
    1.15
     ceremony
    1.07
     upcoming
    1.06
     premiere
    1.05
     Annual
    1.02
     latest
    1.02
    Activations Density 0.251%

    No Known Activations