© 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. 11-RES-JB
    11. 950
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing risks, opportunities, and challenges

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that introduce contrasts or comparisons related to risks and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    escription
    -0.80
    agle
    -0.77
    mitter
    -0.77
    cture
    -0.77
    section
    -0.75
    film
    -0.74
    obook
    -0.73
    ĸļ
    -0.72
    ernaut
    -0.71
     Radio
    -0.71
    POSITIVE LOGITS
     uncertainties
    1.63
     frustrations
    1.61
     weaknesses
    1.55
     shortcomings
    1.55
     setbacks
    1.52
     pitfalls
    1.52
     vulnerabilities
    1.50
     failures
    1.47
     failings
    1.45
     hardships
    1.43
    Activations Density 0.253%

    No Known Activations