© 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. 11-RES-JB
    11. 9311
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational or sequential structure

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing clarity and correcting misunderstandings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cf
    -0.74
    soever
    -0.70
    URA
    -0.67
    Downloadha
    -0.61
     Everywhere
    -0.61
    ardless
    -0.61
     Twice
    -0.60
     Shutterstock
    -0.60
     Large
    -0.60
    paralleled
    -0.59
    POSITIVE LOGITS
     nutshell
    0.91
     backstory
    0.88
     factual
    0.86
     facts
    0.85
     misconceptions
    0.84
    topic
    0.80
     basics
    0.80
     succinct
    0.79
    EStreamFrame
    0.78
     context
    0.77
    Activations Density 0.234%

    No Known Activations