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. 7-RES-JB
    6. 24406
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of things being divided in half

    oai_token-act-pair · gpt-3.5-turbo

    phrases highlighting fractions or portions related to the quantity "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dump
    -0.73
    ãĤ¡
    -0.71
    CLA
    -0.68
    hend
    -0.64
    abl
    -0.61
    trade
    -0.61
    rit
    -0.60
    ded
    -0.59
    no
    -0.59
    weak
    -0.59
    POSITIVE LOGITS
     Sevent
    0.69
     AMERICA
    0.67
    çͰ
    0.66
     GDP
    0.65
    agos
    0.64
    buquerque
    0.63
    ousand
    0.62
    ths
    0.62
     respondents
    0.61
     precincts
    0.61
    Activations Density 0.072%

    No Known Activations