© 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. 3-RES-JB
    11. 6499
    Prev
    Next
    INDEX
    Explanations

    words that intensify the following adjective

    oai_token-act-pair · gpt-3.5-turbo

    the word "very" indicating emphasis or intensification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onent
    -0.80
     Bei
    -0.72
    enegger
    -0.72
    osal
    -0.68
    adelphia
    -0.67
    sburgh
    -0.64
    igate
    -0.64
    course
    -0.63
    è¦ļéĨĴ
    -0.63
    roach
    -0.63
    POSITIVE LOGITS
    STEM
    0.85
     informative
    0.78
     Helpful
    0.75
     Important
    0.74
     Rare
    0.71
    technical
    0.70
     Positive
    0.69
     rare
    0.68
    much
    0.68
     technical
    0.68
    Activations Density 0.037%

    No Known Activations