© 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. 7-RES-JB
    11. 23720
    Prev
    Next
    INDEX
    Explanations

    actions or activities that involve trying, ordering, wearing, making, purchasing, eating, reading, or using items

    oai_token-act-pair · gpt-3.5-turbo

    actions related to purchasing and trying products

    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
    Engineers
    -0.66
     conject
    -0.64
     elector
    -0.60
    ureau
    -0.60
     lenders
    -0.59
    llular
    -0.59
    nel
    -0.58
    laughter
    -0.58
    arty
    -0.58
    lia
    -0.57
    POSITIVE LOGITS
    é¾įå
    0.82
     UD
    0.75
    é¾
    0.74
     THESE
    0.70
     them
    0.69
     oz
    0.68
     these
    0.67
     this
    0.67
     alot
    0.66
     Abyss
    0.65
    Activations Density 0.285%

    No Known Activations