© 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. 7419
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "certain" items or concepts within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "certain" and its variations, indicating references to unspecified or particular items or groups

    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
    inson
    -0.77
     Cum
    -0.75
    DragonMagazine
    -0.72
    TeX
    -0.71
    perse
    -0.70
    ipple
    -0.69
    Bear
    -0.67
     thence
    -0.67
    GD
    -0.67
    INT
    -0.67
    POSITIVE LOGITS
    ties
    1.42
     kinds
    1.04
     wavelengths
    0.92
     types
    0.86
    iated
    0.85
    iating
    0.83
     amount
    0.82
     amounts
    0.81
     shades
    0.80
     combinations
    0.76
    Activations Density 0.025%

    No Known Activations