© 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. 2-RES-JB
    11. 17278
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of accents

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of accents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISTORY
    -0.77
    tc
    -0.75
    gone
    -0.75
    tics
    -0.73
    pg
    -0.72
    SOURCE
    -0.70
    tical
    -0.67
    rd
    -0.64
    cible
    -0.64
    PG
    -0.63
    POSITIVE LOGITS
    uated
    1.55
    uates
    1.41
    uate
    1.33
     accent
    1.31
    uating
    1.23
     accents
    1.10
    uation
    1.01
    uations
    0.87
     spoof
    0.76
    inished
    0.74
    Activations Density 0.013%

    No Known Activations