© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3125
    Prev
    Next
    INDEX
    Explanations

    phrases related to the condition or availability of products for sale

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to product quality and availability

    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
    •single token firings
    Individually fires on words like "Condition", "Shipping", " Shipping", " Condition", "Availability", "manufact", " handmade", and other online shopping words

    No Comments

    Negative Logits
    onomous
    -0.81
     advers
    -0.72
    ndum
    -0.70
    yip
    -0.68
     invoked
    -0.68
    leep
    -0.68
    annah
    -0.67
     truce
    -0.67
    jit
    -0.66
     yawn
    -0.66
    POSITIVE LOGITS
     packaging
    1.29
     manufacture
    1.22
     Warranty
    1.20
     products
    1.19
     shipment
    1.18
     manufacturer
    1.18
    Shipping
    1.17
     Manufact
    1.17
     shipped
    1.17
     manufactured
    1.15
    Activations Density 1.338%

    No Known Activations