© 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. 6262
    Prev
    Next
    INDEX
    Explanations

    positive expressions of support or enthusiasm

    oai_token-act-pair · gpt-3.5-turbo

    instances of support and expressions of care in various contexts

    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
    dar
    -0.80
     Labrador
    -0.70
     lodge
    -0.63
    Interstitial
    -0.61
     princip
    -0.61
     Franch
    -0.60
    cius
    -0.59
     Crown
    -0.59
     Sins
    -0.59
     cutter
    -0.58
    POSITIVE LOGITS
     outp
    1.09
    issance
    0.99
    acing
    0.99
    acer
    0.96
    imates
    0.94
    owers
    0.91
    ersed
    0.88
    inished
    0.88
    ouring
    0.88
     ILCS
    0.86
    Activations Density 0.012%

    No Known Activations