© 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. 6542
    Prev
    Next
    INDEX
    Explanations

    statements that express personal feelings or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the United States in a political or economic context

    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
    */(
    -0.69
    inarily
    -0.68
     advis
    -0.66
    osaurs
    -0.65
     guiActiveUn
    -0.64
    bably
    -0.63
    obyl
    -0.62
     inver
    -0.62
    ventus
    -0.62
     holog
    -0.61
    POSITIVE LOGITS
     Geological
    0.83
    Va
    0.77
    $.
    0.75
     Navy
    0.71
    AAF
    0.71
     Embassy
    0.69
    UA
    0.69
    edu
    0.68
    asc
    0.68
    Org
    0.66
    Activations Density 0.074%

    No Known Activations