© 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. 10-RES-JB
    11. 10101
    Prev
    Next
    INDEX
    Explanations

    terms related to categorization into two distinct groups or types

    oai_token-act-pair · gpt-3.5-turbo

    structures that categorize or classify items or concepts

    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
     wonders
    -0.71
    azel
    -0.63
     notwithstanding
    -0.63
    ITIES
    -0.63
    âĢ¦)
    -0.61
     pores
    -0.61
    lves
    -0.60
    gered
    -0.59
    uary
    -0.58
     nowhere
    -0.58
    POSITIVE LOGITS
     Firstly
    1.10
     Either
    0.93
     Ones
    0.89
    hemat
    0.83
     Those
    0.78
    Firstly
    0.77
     First
    0.77
     Begin
    0.76
     namely
    0.75
    first
    0.74
    Activations Density 0.139%

    No Known Activations