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. 11-RES-JB
    6. 687
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases beginning with "on" in relation to sports

    oai_token-act-pair · gpt-3.5-turbo

    the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Allah
    -0.74
    GOP
    -0.69
    Jess
    -0.67
    abal
    -0.63
    assment
    -0.62
    Relations
    -0.62
    ities
    -0.61
    Requ
    -0.60
    heads
    -0.60
    10000
    -0.58
    POSITIVE LOGITS
     offense
    1.17
     defense
    1.06
    etime
    0.95
     waivers
    0.94
     injured
    0.90
     Opening
    0.89
     Offense
    0.89
     occasion
    0.87
     campus
    0.84
    erous
    0.83
    Activations Density 0.071%

    No Known Activations