© 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. 8-RES-JB
    11. 23426
    Prev
    Next
    INDEX
    Explanations

    words written in Arabic

    oai_token-act-pair · gpt-3.5-turbo

    mentions of language names, particularly Arabic and Spanish

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.90
    ividual
    -0.84
    inson
    -0.83
    urion
    -0.81
    rons
    -0.80
    anmar
    -0.79
    olicy
    -0.78
    cling
    -0.78
    ufact
    -0.78
    vre
    -0.77
    POSITIVE LOGITS
     translation
    1.37
     language
    1.25
     subtitles
    1.23
     languages
    1.19
     pronunciation
    1.17
     translations
    1.17
     diction
    1.13
     dialect
    1.06
     Language
    1.06
     translator
    1.06
    Activations Density 0.100%

    No Known Activations