© 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. 6707
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant focus or conclusion in a text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    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
     regener
    -0.87
     welcome
    -0.86
     challeng
    -0.81
     superiority
    -0.79
     sustainable
    -0.78
     transitions
    -0.77
     beginner
    -0.76
     competitiveness
    -0.76
     sustainability
    -0.76
     climates
    -0.76
    POSITIVE LOGITS
     Investigators
    1.54
     According
    1.53
     Documents
    1.44
    Documents
    1.35
     Sources
    1.34
     Prosecutors
    1.32
     Apparently
    1.29
    According
    1.29
    Investigators
    1.27
     Authorities
    1.24
    Activations Density 0.491%

    No Known Activations