© 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. 8-RES-JB
    11. 14986
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical structures or entities named "shell" that can vary in usage from business contexts to biological contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to shell companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå
    -0.77
    VERTIS
    -0.69
     Moody
    -0.65
    ————————————————
    -0.64
     Gohan
    -0.62
     trave
    -0.60
    riad
    -0.60
    upon
    -0.59
     Mub
    -0.59
     Eisenhower
    -0.59
    POSITIVE LOGITS
    shock
    1.18
    fish
    1.17
    shell
    1.14
    brook
    0.91
     casing
    0.91
    bash
    0.87
    ned
    0.82
    acking
    0.81
     shells
    0.81
    acked
    0.80
    Activations Density 0.044%

    No Known Activations