© 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. 19247
    Prev
    Next
    INDEX
    Explanations

    large numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable references to large numbers or amounts

    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
    æ©Ł
    -0.80
    çīĪ
    -0.72
    çĶŁ
    -0.64
    æĦ
    -0.60
     refreshed
    -0.58
    acas
    -0.58
    Flag
    -0.58
    istered
    -0.56
    ãĤ¸
    -0.55
     plunged
    -0.54
    POSITIVE LOGITS
     depending
    0.88
    depending
    0.85
     achievable
    0.78
     exaggeration
    0.70
     manageable
    0.68
     ballpark
    0.67
    EStreamFrame
    0.66
    blown
    0.66
    %.
    0.66
     coincidence
    0.65
    Activations Density 0.661%

    No Known Activations