© 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. 18643
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and codes

    oai_token-act-pair · gpt-3.5-turbo

    elements related to instructions or commands

    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
    sie
    -0.80
    gettable
    -0.78
    uma
    -0.78
    asse
    -0.75
    imb
    -0.75
    hatt
    -0.74
    iland
    -0.73
    Enlarge
    -0.73
    eli
    -0.72
    embed
    -0.72
    POSITIVE LOGITS
     WW
    0.81
     CM
    0.81
     BF
    0.73
     LL
    0.67
     TBA
    0.67
     FA
    0.65
     SJ
    0.64
     infinity
    0.63
     Milk
    0.63
     Soph
    0.63
    Activations Density 0.341%

    No Known Activations