© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20342
    Prev
    Next
    INDEX
    Explanations

    the word "week" in a text document

    oai_token-act-pair · gpt-3.5-turbo

    references to the current week and events or updates associated with it

    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
    jri
    -0.83
    ashtra
    -0.68
    amate
    -0.67
     redistributed
    -0.63
    Fil
    -0.63
     Gems
    -0.62
    iced
    -0.61
    ected
    -0.60
    ufficient
    -0.60
    itars
    -0.59
    POSITIVE LOGITS
    days
    1.20
    night
    1.11
    DAY
    1.01
    iversary
    0.98
     Ago
    0.96
     afternoon
    0.90
    day
    0.84
     ago
    0.83
     week
    0.82
    bourne
    0.82
    Activations Density 0.043%

    No Known Activations