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. 10-RES-JB
    6. 24215
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions, bids, and deals for players in sports teams

    oai_token-act-pair · gpt-3.5-turbo

    financial figures related to sports transfers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bicycl
    -0.86
    colored
    -0.81
    NPR
    -0.81
    boro
    -0.80
     humor
    -0.77
     Accountability
    -0.76
     Hawai
    -0.76
     Appalachian
    -0.74
    keyes
    -0.72
    uminum
    -0.72
    POSITIVE LOGITS
     £
    1.58
     enqu
    1.41
    £
    1.37
     rumours
    1.32
     âĤ¬
    1.31
     Tottenham
    1.28
     Fifa
    1.26
    ottenham
    1.20
     (£
    1.20
     Anfield
    1.18
    Activations Density 0.811%

    No Known Activations