© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3546
    Prev
    Next
    INDEX
    Explanations

    discount codes or special offers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Add" indicating a call to action related to adding items, possibly in a shopping or inventory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maker
    -0.69
    ··
    -0.68
     Pulse
    -0.64
     Shades
    -0.62
    creen
    -0.62
    PATH
    -0.61
    APH
    -0.60
     THR
    -0.59
     Falcon
    -0.59
    NING
    -0.58
    POSITIVE LOGITS
    endum
    1.46
    ition
    1.31
    ressing
    1.29
    icted
    1.26
    resses
    1.25
    itions
    1.24
    itional
    1.21
    icts
    1.20
    itionally
    1.13
    ictive
    1.13
    Activations Density 0.033%

    No Known Activations