© 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. 5409
    Prev
    Next
    INDEX
    Explanations

    terms related to time sequences and temporal processing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to time and temporal processes

    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
    iants
    -0.90
    ortment
    -0.86
    gling
    -0.86
    rd
    -0.85
    iance
    -0.83
    rim
    -0.81
    acles
    -0.78
    warts
    -0.77
    riad
    -0.77
    endor
    -0.76
    POSITIVE LOGITS
     lobe
    0.95
    brate
    0.75
    ptoms
    0.71
     Remastered
    0.71
     neigh
    0.71
     temporal
    0.69
     Extend
    0.69
     Correction
    0.68
     reven
    0.68
     lords
    0.68
    Activations Density 0.013%

    No Known Activations