© 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. 10-RES-JB
    11. 13691
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical engineering, such as "electrical," "resistance," and "wires."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electrical engineering and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itia
    -0.82
    naire
    -0.75
    lain
    -0.75
    aird
    -0.70
     Archdemon
    -0.69
    nered
    -0.69
    isl
    -0.68
     Leth
    -0.68
    ality
    -0.68
    fare
    -0.65
    POSITIVE LOGITS
     circuitry
    1.20
    onductor
    1.09
     wiring
    1.09
     circuits
    1.09
     impedance
    0.98
     capacitor
    0.97
    uctor
    0.95
     wires
    0.95
     voltage
    0.93
     electrical
    0.92
    Activations Density 0.071%

    No Known Activations