© 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. 18529
    Prev
    Next
    INDEX
    Explanations

    text in a foreign language, specifically Cyrillic characters and potentially Russian content

    oai_token-act-pair · gpt-3.5-turbo

    specific non-standard or non-ASCII characters in the text

    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
    BuyableInstoreAndOnline
    -0.84
    ebted
    -0.77
    cliffe
    -0.70
     Faw
    -0.70
     Starr
    -0.68
     Sapphire
    -0.67
    bows
    -0.64
     Druid
    -0.62
    Fish
    -0.62
    oba
    -0.61
    POSITIVE LOGITS
    ¹
    1.39
    ¶
    1.38
    ·
    1.37
    ±
    1.31
    ¿
    1.28
    ³
    1.27
    ¤
    1.11
    ¡
    1.10
    ĺ
    1.06
    Ĵ
    1.03
    Activations Density 0.020%

    No Known Activations