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. 4-RES-JB
    6. 18222
    Prev
    Next
    INDEX
    Explanations

    terms related to enrichment, whether it's enriching soil, uranium, education, or lives

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to the process of enriching materials or experiences

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

    No Comments

    Negative Logits
    soDeliveryDate
    -0.78
     Assassins
    -0.78
     Warriors
    -0.70
    olver
    -0.69
    Hyper
    -0.68
    WD
    -0.66
     Scream
    -0.65
    DragonMagazine
    -0.64
    fight
    -0.64
    prototype
    -0.64
    POSITIVE LOGITS
     enrich
    1.37
     enriched
    1.11
     Seym
    1.10
     enrichment
    1.07
    itures
    1.07
     uranium
    1.01
    ments
    0.97
    riched
    0.90
     richer
    0.89
     tremend
    0.88
    Activations Density 0.009%

    No Known Activations