© 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. 1-RES-JB
    11. 7322
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "halving"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "halachic" concepts or references related to Jewish law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URE
    -0.83
    ULTS
    -0.79
     Provider
    -0.77
    URES
    -0.77
    Library
    -0.75
    Description
    -0.73
    Methods
    -0.73
    æĸ¹
    -0.72
     Orig
    -0.71
    ãģķ
    -0.70
    POSITIVE LOGITS
     hal
    1.23
    tering
    0.97
    ifax
    0.96
    ftime
    0.92
    umph
    0.90
    haul
    0.89
    ving
    0.89
    ved
    0.86
    vati
    0.86
    pling
    0.83
    Activations Density 0.003%

    No Known Activations