© 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. 9-RES-JB
    11. 21188
    Prev
    Next
    INDEX
    Explanations

    references to emotional or dramatic events related to personal interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of surprise or unexpected discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -0.71
    eatures
    -0.68
    serving
    -0.63
     millenn
    -0.63
    ymm
    -0.62
     OPS
    -0.59
    site
    -0.57
    Times
    -0.56
    imester
    -0.55
    ISC
    -0.55
    POSITIVE LOGITS
     instantly
    1.16
     immediately
    1.16
     instinctively
    0.98
     exclaimed
    0.97
     wondered
    0.96
     panicked
    0.94
     intrigued
    0.93
     decided
    0.90
     clicked
    0.89
     promptly
    0.89
    Activations Density 0.484%

    No Known Activations