© 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. 1-RES-JB
    11. 3307
    Prev
    Next
    INDEX
    Explanations

    references to activities or events happening at night

    oai_token-act-pair · gpt-3.5-turbo

    references to "night."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achev
    -0.80
    atem
    -0.74
    inters
    -0.73
    Æ
    -0.73
    OTUS
    -0.72
    FAULT
    -0.70
    verett
    -0.70
    ettle
    -0.69
    xon
    -0.68
    emort
    -0.68
    POSITIVE LOGITS
     nights
    1.01
     night
    0.97
    night
    0.93
     afternoon
    0.79
    mares
    0.78
    worms
    0.77
     twilight
    0.74
    fall
    0.74
     evenings
    0.74
    dream
    0.73
    Activations Density 0.028%

    No Known Activations