© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 21789
    Prev
    Next
    INDEX
    Explanations

    sentences containing exclamation marks and symbols

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory punctuation and words that convey excitement or emphasis

    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
     strugg
    -0.77
     satell
    -0.72
     economy
    -0.67
     answ
    -0.66
     proble
    -0.65
     incap
    -0.64
     groundwork
    -0.64
     conflic
    -0.64
     waste
    -0.64
     attorney
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.05
     Originally
    0.97
     Located
    0.96
    ï¸
    0.95
     Congratulations
    0.94
     Unfortunately
    0.91
     Designed
    0.89
     This
    0.88
     Which
    0.87
    Created
    0.87
    Activations Density 0.207%

    No Known Activations