© 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. 1448
    Prev
    Next
    INDEX
    Explanations

    words related to packaging and packs of items

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pack" and its variations

    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
    Downloadha
    -0.74
    nesota
    -0.70
    ffen
    -0.70
    DonaldTrump
    -0.68
    abama
    -0.68
     obser
    -0.68
    utory
    -0.66
     Cald
    -0.66
    sembly
    -0.66
    izon
    -0.64
    POSITIVE LOGITS
    aging
    1.26
    ages
    1.22
    agers
    1.12
    pack
    1.11
    aged
    1.03
    erness
    1.01
    ager
    0.97
    packs
    0.91
    rats
    0.89
    AGES
    0.88
    Activations Density 0.028%

    No Known Activations