© 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. 14025
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     torpedo
    -0.88
     loft
    -0.87
     satell
    -0.80
    avorite
    -0.80
     maritime
    -0.80
     estates
    -0.80
     mushroom
    -0.77
     cryptoc
    -0.77
     craft
    -0.77
     sailing
    -0.76
    POSITIVE LOGITS
    âĢ
    2.10
     âĢ
    1.68
    »
    1.36
    âĸł
    1.34
    âĢł
    1.31
    ãĢ
    1.30
    **
    1.26
    âĺ
    1.16
    âľ
    1.13
    ��
    1.11
    Activations Density 0.341%

    No Known Activations