© 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. 4-RES-JB
    11. 22293
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of 'emblazoning' or 'embellishment'

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "emblazon" and related variations

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

    No Comments

    Negative Logits
    yip
    -0.81
     Fas
    -0.77
    ategory
    -0.65
     Bengal
    -0.62
     Pigs
    -0.62
     requisite
    -0.62
     Variant
    -0.61
    hillary
    -0.60
     saline
    -0.60
     fares
    -0.59
    POSITIVE LOGITS
    acements
    0.86
    ciating
    0.83
    opol
    0.83
    agement
    0.79
    andum
    0.77
    ment
    0.75
    mental
    0.74
    icans
    0.70
    ogyn
    0.67
    ITNESS
    0.67
    Activations Density 0.070%

    No Known Activations