© 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. 4-RES-JB
    11. 3629
    Prev
    Next
    INDEX
    Explanations

    mentions of specific weekday nights

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week, particularly nights associated with events

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

    No Comments

    Negative Logits
    UTF
    -0.74
    covered
    -0.73
    absor
    -0.73
    ignant
    -0.73
    commun
    -0.73
    infect
    -0.70
    tnc
    -0.69
    rec
    -0.69
    recated
    -0.69
    pid
    -0.68
    POSITIVE LOGITS
     afternoon
    0.84
     night
    0.78
     evening
    0.74
    night
    0.74
     mornings
    0.72
     UPDATE
    0.70
     morning
    0.69
     nights
    0.69
     Evening
    0.69
     eve
    0.67
    Activations Density 0.051%

    No Known Activations