© 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. 8114
    Prev
    Next
    INDEX
    Explanations

    numerical quantities accompanied by some form of quantifier like "Two" or "Four"

    oai_token-act-pair · gpt-3.5-turbo

    numerical references, particularly counts and groupings related to people or entities

    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
    ifice
    -0.88
    oper
    -0.66
    ivism
    -0.65
     agre
    -0.64
    ocracy
    -0.63
    ICO
    -0.63
    same
    -0.63
    omo
    -0.62
     guiActiveUnfocused
    -0.62
     theirs
    -0.62
    POSITIVE LOGITS
    teen
    1.46
    een
    1.19
    Thirty
    1.02
     hundred
    0.98
     weeks
    0.95
     months
    0.95
     Months
    0.93
     Hours
    0.91
     days
    0.90
     years
    0.89
    Activations Density 0.126%

    No Known Activations