© 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. 1-RES-JB
    11. 9496
    Prev
    Next
    INDEX
    Explanations

    numbers within text with the word "Very"

    oai_token-act-pair · gpt-3.5-turbo

    the emphasis on the word "very" to indicate intensity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.83
    osal
    -0.81
    æ©
    -0.69
     rooft
    -0.68
    roach
    -0.65
    onis
    -0.65
    ovie
    -0.65
    orate
    -0.64
    ometry
    -0.62
    yll
    -0.62
    POSITIVE LOGITS
    Rare
    1.13
     Rare
    0.97
    Very
    0.95
    Uncommon
    0.95
     Important
    0.85
    entimes
    0.82
    Extreme
    0.81
     Interesting
    0.76
     Very
    0.76
     informative
    0.76
    Activations Density 0.013%

    No Known Activations