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. 8-RES-JB
    6. 16652
    Prev
    Next
    INDEX
    Explanations

    prepositions 'on the'

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases indicating situational contexts

    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
    Commerce
    -0.63
    2019
    -0.60
    INESS
    -0.59
    orically
    -0.59
    DragonMagazine
    -0.57
    RL
    -0.57
    OULD
    -0.56
     trough
    -0.56
    Includes
    -0.56
    SourceFile
    -0.56
    POSITIVE LOGITS
     verge
    1.00
    etime
    0.99
    stage
    0.99
    lined
    0.94
     behalf
    0.93
    site
    0.93
    ibaba
    0.90
     board
    0.89
     lockdown
    0.89
    itored
    0.88
    Activations Density 0.107%

    No Known Activations