© 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. 4-RES-JB
    11. 7100
    Prev
    Next
    INDEX
    Explanations

    dates expressed in a "year-season" format

    oai_token-act-pair · gpt-3.5-turbo

    numerical information related to sports seasons

    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
    yna
    -0.61
    paralle
    -0.60
    phy
    -0.60
    gie
    -0.59
     popped
    -0.59
    icates
    -0.58
    pload
    -0.58
    rote
    -0.57
    ilyn
    -0.57
     copy
    -0.57
    POSITIVE LOGITS
    å¹
    0.82
    20439
    0.77
     attRot
    0.71
    EVA
    0.69
     Hels
    0.66
    çīĪ
    0.66
     Fourth
    0.65
    ridge
    0.65
    âĶĢâĶĢ
    0.65
     onwards
    0.64
    Activations Density 0.048%

    No Known Activations