© 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. 4-RES-JB
    6. 13380
    Prev
    Next
    INDEX
    Explanations

    references to time periods such as "decades"

    oai_token-act-pair · gpt-3.5-turbo

    references to long periods of time spanning several decades

    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
    Package
    -0.72
    iqu
    -0.68
    ople
    -0.64
    ramid
    -0.61
    Plug
    -0.61
     SV
    -0.61
     Syndicate
    -0.61
     Alpha
    -0.61
     Aether
    -0.60
    endar
    -0.60
    POSITIVE LOGITS
     ago
    0.98
    arily
    0.79
    ĸļ
    0.79
     spanning
    0.73
     Ago
    0.70
     onward
    0.70
     hindsight
    0.68
     Lauder
    0.67
     Coffin
    0.66
    å§«
    0.66
    Activations Density 0.032%

    No Known Activations