© 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. 12555
    Prev
    Next
    INDEX
    Explanations

    action verbs related to monitoring, sticking, leaving, telling, letting, doing, saying, keeping, making, eating, updating, staying, getting, continuing, enjoying, making, updating

    oai_token-act-pair · gpt-3.5-turbo

    expressions of future intentions or commitments

    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
     guiActiveUnfocused
    -0.69
     patriarch
    -0.65
    Engineers
    -0.64
     propelled
    -0.62
     Gad
    -0.62
     Gap
    -0.60
     entangled
    -0.60
    REE
    -0.59
     Colleges
    -0.59
    ELD
    -0.57
    POSITIVE LOGITS
     myself
    1.11
     gladly
    0.88
    poke
    0.87
    aido
    0.83
    eeee
    0.79
     reiterate
    0.78
    avis
    0.77
     recommend
    0.74
     my
    0.73
     ital
    0.72
    Activations Density 0.362%

    No Known Activations