Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1637
    Prev
    Next
    INDEX
    Explanations

    the phrase "change is in the air"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the phrase "in the" or "in" at various points throughout the text

    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
    IDA
    -0.77
     suscept
    -0.70
    Statement
    -0.69
    cia
    -0.66
     initials
    -0.64
    Independent
    -0.64
    QL
    -0.62
    SourceFile
    -0.62
     Alone
    -0.61
     Together
    -0.59
    POSITIVE LOGITS
    escap
    1.32
     jeopardy
    1.11
    ext
    1.01
     flux
    0.99
     danger
    0.90
    ching
    0.89
     peril
    0.88
     vain
    0.87
     sight
    0.87
    ked
    0.85
    Activations Density 0.079%

    No Known Activations