© 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. 0-RES-JB
    11. 11360
    Prev
    Next
    INDEX
    Explanations

    references to the act of escaping or narrowly avoiding something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "escaped" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bench
    -0.70
    kus
    -0.70
    MA
    -0.70
     workload
    -0.67
     Vit
    -0.63
     Design
    -0.62
    review
    -0.62
     recommendation
    -0.62
     Bench
    -0.62
    design
    -0.62
    POSITIVE LOGITS
     escaped
    3.80
     escapes
    2.46
     escaping
    2.27
     escape
    2.13
     survived
    1.76
     fled
    1.73
    escape
    1.56
     Escape
    1.41
     perished
    1.41
     avoided
    1.30
    Activations Density 0.018%

    No Known Activations