© 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. 4-RES-JB
    11. 1063
    Prev
    Next
    INDEX
    Explanations

    numerical values with specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those that appear to represent times or measurements

    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
    emade
    -0.83
    inals
    -0.76
    checked
    -0.73
    bara
    -0.73
    names
    -0.72
    eway
    -0.72
    aina
    -0.72
    inges
    -0.72
    enment
    -0.71
    essen
    -0.71
    POSITIVE LOGITS
     ILCS
    1.07
     MHz
    0.93
    MHz
    0.84
    6666
    0.81
    æ©Ł
    0.78
    576
    0.77
    OPLE
    0.75
    597
    0.71
    588
    0.68
    806
    0.68
    Activations Density 0.048%

    No Known Activations