© 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. 11932
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking action or making changes

    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
    ère
    -0.69
     Sloan
    -0.62
     thanking
    -0.60
    eret
    -0.59
     telling
    -0.57
     referring
    -0.56
     specializing
    -0.56
    orsi
    -0.55
     Ãī
    -0.55
     extending
    -0.54
    POSITIVE LOGITS
     oneself
    0.97
     Yourself
    0.72
    olitical
    0.70
    endas
    0.68
    iped
    0.61
     wrong
    0.59
     idols
    0.58
    rows
    0.57
    pless
    0.57
    mercial
    0.56
    Activations Density 0.948%

    No Known Activations