© 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. 3-RES-JB
    11. 11483
    Prev
    Next
    INDEX
    Explanations

    announcements made on a specific day

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "today" indicating recent announcements or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.81
    sed
    -0.78
    chest
    -0.71
    char
    -0.70
    egal
    -0.70
    este
    -0.69
    sac
    -0.68
    aden
    -0.67
    gans
    -0.66
     Conquer
    -0.66
    POSITIVE LOGITS
     afternoon
    1.27
     morning
    1.23
     evening
    1.06
     mornings
    0.94
     Tonight
    0.85
    days
    0.84
    morning
    0.82
    terday
    0.81
     TODAY
    0.80
     midday
    0.77
    Activations Density 0.048%

    No Known Activations