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. 15123
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a range or interval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "between" indicating a range or interval

    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
    gow
    -0.83
    OGR
    -0.73
    matically
    -0.72
    pot
    -0.72
    matic
    -0.68
    unc
    -0.68
    omen
    -0.66
    olf
    -0.65
    istani
    -0.63
    awaru
    -0.62
    POSITIVE LOGITS
     halves
    1.12
     extremes
    0.96
     sexes
    0.95
     rounds
    0.95
     genders
    0.95
     bouts
    0.94
     paragraphs
    0.86
     phases
    0.84
     worlds
    0.83
     layers
    0.83
    Activations Density 0.045%

    No Known Activations