© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23834
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of "days" with numbers indicating the significance of time periods

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "days."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emort
    -0.89
    acted
    -0.73
    inav
    -0.71
    umbn
    -0.70
    malink
    -0.69
    cientious
    -0.69
    ilde
    -0.69
    Reviewer
    -0.68
    emale
    -0.67
    icide
    -0.65
    POSITIVE LOGITS
     ago
    1.13
    days
    1.06
    pring
    1.03
     Ago
    0.91
    dream
    0.90
     elapsed
    0.87
    terday
    0.81
    DAY
    0.79
    hift
    0.79
     days
    0.79
    Activations Density 0.032%

    No Known Activations