© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4909
    Prev
    Next
    INDEX
    Explanations

    words related to electrical wiring, such as cables, wires, bolts, and connectors

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of electrical wires and cables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.78
    ãĥ´
    -0.71
    Attempt
    -0.69
    âĸ¬
    -0.67
    Delivery
    -0.67
    lier
    -0.67
    Hur
    -0.67
    Decre
    -0.65
    Penn
    -0.65
    Cele
    -0.63
    POSITIVE LOGITS
    mith
    1.63
    hops
    1.22
    paces
    1.19
    ilver
    1.17
    poons
    1.15
    heet
    1.14
    pace
    1.13
    cale
    1.12
    ongs
    1.10
    hooting
    1.08
    Activations Density 0.105%

    No Known Activations