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. 457
    Prev
    Next
    INDEX
    Explanations

    verbs related to lasting or endurance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to duration and permanence of events or conditions

    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
    agon
    -0.72
    ilings
    -0.69
    idia
    -0.67
    ription
    -0.66
    anyon
    -0.63
    axter
    -0.61
    racuse
    -0.61
    death
    -0.60
    ighters
    -0.58
    arte
    -0.57
    POSITIVE LOGITS
     longer
    1.07
     indefinitely
    1.02
     forever
    1.00
     awhile
    0.87
     longest
    0.84
     until
    0.79
     uninterrupted
    0.78
     minute
    0.78
     weeks
    0.78
     months
    0.75
    Activations Density 0.057%

    No Known Activations