© 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. 4-RES-JB
    11. 22194
    Prev
    Next
    INDEX
    Explanations

    phrases indicating division or categorization

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to division or categorization

    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
     confir
    -0.74
     Archdemon
    -0.72
     nud
    -0.63
    naissance
    -0.62
    ogle
    -0.61
     outp
    -0.61
    SPONSORED
    -0.61
     tremend
    -0.60
     Rutherford
    -0.59
    onda
    -0.58
    POSITIVE LOGITS
     thirds
    0.81
     geographically
    0.77
     sexes
    0.73
    ombat
    0.69
     territory
    0.68
     factions
    0.68
    cipl
    0.67
     halves
    0.67
    imilar
    0.66
     Territories
    0.66
    Activations Density 0.203%

    No Known Activations