© 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. 1-RES-JB
    11. 3889
    Prev
    Next
    INDEX
    Explanations

    references to the word "gate"

    oai_token-act-pair · gpt-3.5-turbo

    references to gates or barriers, indicating a focus on physical or metaphorical entry points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subp
    -0.73
     constitu
    -0.66
     own
    -0.65
     skilled
    -0.65
     specialized
    -0.64
     blueprint
    -0.62
    inances
    -0.61
    >>>>>>>>
    -0.58
     marrow
    -0.57
    ynt
    -0.57
    POSITIVE LOGITS
    gate
    1.49
    Gate
    1.11
    way
    0.93
    boro
    0.87
    ardless
    0.86
    pole
    0.85
    ways
    0.83
    cloth
    0.83
    math
    0.82
    watch
    0.82
    Activations Density 0.008%

    No Known Activations