© 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. 7-RES-JB
    11. 17273
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decimal systems or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zn
    -0.65
     gal
    -0.62
    liners
    -0.60
    swick
    -0.60
     vomit
    -0.60
     Gallagher
    -0.58
    utra
    -0.57
     sidel
    -0.57
    belt
    -0.57
    liner
    -0.56
    POSITIVE LOGITS
    pter
    0.83
    ributed
    0.79
    ¬¼
    0.76
    urrencies
    0.73
    alogue
    0.72
    rypt
    0.71
     partName
    0.70
    TPP
    0.70
    SQL
    0.68
    ISION
    0.68
    Activations Density 0.095%

    No Known Activations