© 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. 10-RES-JB
    11. 9922
    Prev
    Next
    INDEX
    Explanations

    characters from different languages, especially Cyrillic, related to medical studies or research

    oai_token-act-pair · gpt-3.5-turbo

    specific special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Starr
    -0.76
     Kee
    -0.69
    atche
    -0.67
     Lauder
    -0.66
     Roe
    -0.62
     oral
    -0.60
     Riley
    -0.59
     forgiving
    -0.59
     strategically
    -0.59
     Sapphire
    -0.58
    POSITIVE LOGITS
    ÑĤ
    1.69
    к
    1.48
    оÐ
    1.38
    и
    1.34
    Ñĭ
    1.32
    л
    1.30
    Ñĥ
    1.28
    ÑĮ
    1.25
    Ñģ
    1.23
    а
    1.21
    Activations Density 0.011%

    No Known Activations