© 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. 10-RES-JB
    11. 16669
    Prev
    Next
    INDEX
    Explanations

    references to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify or specify amounts related to data and memory usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    few
    -0.92
    heses
    -0.84
    months
    -0.84
    States
    -0.81
    entimes
    -0.76
    heid
    -0.76
    kens
    -0.74
    999
    -0.73
    artist
    -0.73
     Cosponsors
    -0.72
    POSITIVE LOGITS
     usable
    0.96
     extra
    0.89
     additional
    0.86
     uninterrupted
    0.85
     unprotected
    0.82
     ground
    0.79
     cumulative
    0.79
     equipment
    0.78
     concentrated
    0.78
     material
    0.78
    Activations Density 0.078%

    No Known Activations