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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 3252
    Prev
    Next
    INDEX
    Explanations

    phrases or commands related to adding items to a cart or list

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to adding items, specifically in a shopping or cart context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gel
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    Ãį
    -0.67
    wav
    -0.65
     Gibbs
    -0.65
    falls
    -0.65
    DEM
    -0.63
    )].
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    姫
    -0.61
    POSITIVE LOGITS
    endum
    1.24
    ition
    1.17
    itions
    1.11
    resses
    1.10
    itionally
    1.04
    ickets
    1.01
    add
    1.01
    icted
    1.00
    itional
    0.97
    ictive
    0.96
    Activations Density 0.015%

    No Known Activations