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. 10-RES-JB
    6. 22260
    Prev
    Next
    INDEX
    Explanations

    information related to promotions or special offers

    oai_token-act-pair · gpt-3.5-turbo

    references to individual purchasers and ticket sales for events

    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
     Harm
    -0.73
    inventoryQuantity
    -0.71
    quickShipAvailable
    -0.70
     Techniques
    -0.69
     predictable
    -0.68
     abras
    -0.68
    MpServer
    -0.68
    sein
    -0.68
     proverb
    -0.68
     interrogation
    -0.67
    POSITIVE LOGITS
     purchased
    1.29
     redeemed
    1.29
     subscribed
    1.27
     login
    1.26
     purchase
    1.26
     enroll
    1.23
     enrolled
    1.23
     registered
    1.15
    registered
    1.13
     redeem
    1.12
    Activations Density 0.301%

    No Known Activations