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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 20905
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting records or breaking records

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to record-setting or breaking events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ido
    -0.80
     moder
    -0.73
    lesh
    -0.65
    imaru
    -0.63
    afi
    -0.63
     unres
    -0.61
     econom
    -0.61
     Galile
    -0.61
    ghan
    -0.61
    imov
    -0.60
    POSITIVE LOGITS
    record
    0.84
     deeds
    0.75
     achievements
    0.74
     rainfall
    0.70
    keeping
    0.70
     accomplishments
    0.69
    breaking
    0.69
    collection
    0.68
     record
    0.67
    recorded
    0.67
    Activations Density 0.273%

    No Known Activations