© 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. 8-RES-JB
    11. 18564
    Prev
    Next
    INDEX
    Explanations

    details about roles and affiliations of individuals in various organizations

    oai_token-act-pair · gpt-3.5-turbo

    information about individuals with notable careers and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intent
    -0.78
    elo
    -0.74
    enment
    -0.66
    estamp
    -0.66
     stupidity
    -0.66
    ifice
    -0.65
    upid
    -0.64
    uers
    -0.64
    lag
    -0.63
    che
    -0.63
    POSITIVE LOGITS
     liaison
    0.82
     adjunct
    0.81
     numerous
    0.79
     lia
    0.78
     trustee
    0.77
     extensively
    0.77
     occasional
    0.75
     honorary
    0.75
     induct
    0.75
     Vis
    0.74
    Activations Density 0.428%

    No Known Activations