© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22486
    Prev
    Next
    INDEX
    Explanations

    words related to nighttime activities or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to nighttime or nightlife

    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
    achev
    -0.81
    xon
    -0.80
    pta
    -0.79
    cules
    -0.74
    qqa
    -0.72
    emort
    -0.71
    berman
    -0.69
    qua
    -0.69
     Canaver
    -0.68
    rompt
    -0.68
    POSITIVE LOGITS
    cap
    1.03
    fall
    1.01
    mares
    1.00
    life
    0.98
    mar
    0.94
    club
    0.89
    mare
    0.86
    light
    0.86
     sky
    0.80
     ow
    0.78
    Activations Density 0.045%

    No Known Activations