© 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. 10-RES-JB
    11. 2917
    Prev
    Next
    INDEX
    Explanations

    words related to characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various sectors, demographics, and health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.79
     Wife
    -0.74
     Empty
    -0.71
    bye
    -0.70
    ynthesis
    -0.69
     Goodbye
    -0.68
     Apprentice
    -0.67
    ructose
    -0.66
    erey
    -0.65
     Piano
    -0.65
    POSITIVE LOGITS
     categories
    1.59
     formats
    1.52
     disciplines
    1.51
     contexts
    1.49
     types
    1.46
     configurations
    1.41
     sectors
    1.38
     modes
    1.37
     scenarios
    1.36
     entities
    1.36
    Activations Density 0.360%

    No Known Activations