© 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. 22965
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes being carried out on a large scale

    oai_token-act-pair · gpt-3.5-turbo

    actions related to shutdowns, closures, and arrests

    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
    whatever
    -0.67
    something
    -0.61
    yip
    -0.60
    leader
    -0.56
    comes
    -0.56
    tone
    -0.55
    erity
    -0.55
     Darius
    -0.54
     prompt
    -0.54
    bral
    -0.53
    POSITIVE LOGITS
     apiece
    0.92
     consecut
    0.90
    abouts
    0.87
     individually
    0.81
     respectively
    0.79
     nationwide
    0.79
     simultaneously
    0.78
     throughout
    0.75
     worldwide
    0.75
     besides
    0.74
    Activations Density 0.348%

    No Known Activations