© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5251
    Prev
    Next
    INDEX
    Explanations

    times written in a specific format (hours and minutes) accompanied by certain days of the week

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ò
    -1.04
     eleph
    -1.03
     enthusi
    -0.96
    ñ
    -0.93
    aditional
    -0.92
    ě
    -0.90
    ĕ
    -0.89
    À
    -0.89
    oreAnd
    -0.89
    Ě
    -0.88
    POSITIVE LOGITS
    m
    1.03
    meter
    0.86
    pm
    0.83
    ms
    0.79
    mur
    0.74
    mk
    0.73
    md
    0.72
    Ms
    0.72
    ped
    0.71
    mat
    0.71
    Activations Density 0.028%

    No Known Activations