© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6678
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions about accents, particularly detailed and specific ones

    oai_token-act-pair · gpt-3.5-turbo

    words related to different types of accents in speech

    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
    tics
    -0.74
     =================================
    -0.69
    tc
    -0.69
    tical
    -0.68
    PAR
    -0.68
    anski
    -0.67
    Internal
    -0.67
    advertising
    -0.66
    cible
    -0.66
    ISTORY
    -0.65
    POSITIVE LOGITS
    uated
    1.45
    uates
    1.35
    uate
    1.29
    uating
    1.18
     accent
    1.18
     accents
    1.06
    uation
    0.96
    uations
    0.86
     fastball
    0.78
     pronunciation
    0.78
    Activations Density 0.017%

    No Known Activations