© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 20340
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, specifically involving the concept of 24 hours

    oai_token-act-pair · gpt-3.5-turbo

    references to a 24-hour time frame or coverage

    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
    inav
    -0.81
    irie
    -0.80
    Creat
    -0.75
    spl
    -0.71
    riv
    -0.70
    animous
    -0.70
    ortium
    -0.69
    rect
    -0.69
    Catalog
    -0.68
    DL
    -0.67
    POSITIVE LOGITS
     consecut
    0.92
    ruary
    0.89
     elapsed
    0.88
     thereafter
    0.87
    endment
    0.86
     ago
    0.82
    days
    0.77
    undred
    0.77
     olds
    0.76
     onwards
    0.74
    Activations Density 0.069%

    No Known Activations