© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23143
    Prev
    Next
    INDEX
    Explanations

    phrases related to purchasing or pre-ordering items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ordering and pre-orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Foley
    -0.65
     Stall
    -0.64
     Tut
    -0.63
     cheek
    -0.62
     technology
    -0.61
     glide
    -0.61
     film
    -0.61
     hops
    -0.58
     takedown
    -0.58
     facial
    -0.58
    POSITIVE LOGITS
    ordered
    4.36
    ordering
    2.62
    orders
    2.53
    order
    2.13
     ordered
    1.43
    Order
    1.36
    organized
    1.34
    ORD
    1.24
    Ord
    1.23
     ORDER
    1.18
    Activations Density 0.011%

    No Known Activations