© 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. 6-RES-JB
    11. 17116
    Prev
    Next
    INDEX
    Explanations

    phrases indicating back-and-forth movement or exchange

    oai_token-act-pair · gpt-3.5-turbo

    references to movement or interactions described as "back and forth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obal
    -0.77
    ENA
    -0.77
    iov
    -0.74
    ogi
    -0.73
    CVE
    -0.69
    wan
    -0.67
     Amend
    -0.66
     Vie
    -0.65
    weather
    -0.64
    conn
    -0.64
    POSITIVE LOGITS
    forth
    0.88
    ilaterally
    0.86
     between
    0.86
    )=(
    0.80
     interchange
    0.80
     inco
    0.75
     sides
    0.71
     impulses
    0.71
     mating
    0.70
     dstg
    0.69
    Activations Density 0.012%

    No Known Activations