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. 17893
    Prev
    Next
    INDEX
    Explanations

    verbs related to earning or gaining something

    oai_token-act-pair · gpt-3.5-turbo

    words related to earning or obtaining something

    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
     illum
    -0.69
     Strait
    -0.65
     Gillespie
    -0.61
     bottleneck
    -0.60
     gestation
    -0.59
    dating
    -0.58
    pour
    -0.58
     intestine
    -0.58
     densely
    -0.57
    yrus
    -0.57
    POSITIVE LOGITS
    hardt
    0.84
     certs
    0.80
     certificates
    0.79
     laure
    0.79
     badges
    0.77
     accol
    0.76
    owship
    0.75
    ancial
    0.72
    ËĪ
    0.72
     earn
    0.71
    Activations Density 0.035%

    No Known Activations