© 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. 9-RES-JB
    11. 18431
    Prev
    Next
    INDEX
    Explanations

    years mentioned in historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     locker
    -0.78
     upgr
    -0.77
     assurance
    -0.74
     peers
    -0.73
     slightest
    -0.73
     homework
    -0.72
     zone
    -0.72
     advis
    -0.71
     bench
    -0.70
     flagged
    -0.69
    POSITIVE LOGITS
     Later
    1.58
     Eventually
    1.54
     Afterwards
    1.40
     Shortly
    1.37
     During
    1.34
     Ironically
    1.30
     Unfortunately
    1.24
     Initially
    1.23
     Following
    1.22
     Since
    1.21
    Activations Density 0.446%

    No Known Activations