Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 6766
    Prev
    Next
    INDEX
    Explanations

    information related to product shipping and ordering

    oai_token-act-pair · gpt-3.5-turbo

    information related to shipping and order fulfillment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     halluc
    -0.72
     voc
    -0.70
     eaves
    -0.70
     yawn
    -0.69
     consciously
    -0.67
    hab
    -0.67
    ognitive
    -0.66
     cortical
    -0.66
     wielded
    -0.65
    aughs
    -0.65
    POSITIVE LOGITS
     Shipping
    1.51
     shipment
    1.46
     Delivery
    1.43
    Shipping
    1.42
    Delivery
    1.39
     USPS
    1.36
     invoice
    1.34
     shipping
    1.33
     courier
    1.24
     delivery
    1.24
    Activations Density 0.605%

    No Known Activations