© 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. 2-RES-JB
    11. 12696
    Prev
    Next
    INDEX
    Explanations

    mentions or references to "Ofsted," an organization associated with school inspections and evaluations, often repeated with high activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of an organization named "Ofsted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.66
     nom
    -0.59
     deduct
    -0.59
    iewicz
    -0.58
    ournal
    -0.57
     Gaw
    -0.57
     oxy
    -0.57
     classy
    -0.57
     Taiwanese
    -0.57
     distilled
    -0.57
    POSITIVE LOGITS
    sted
    1.15
    nton
    0.87
    ric
    0.86
    dden
    0.83
    emouth
    0.83
    ragon
    0.82
    le
    0.82
    leneck
    0.80
    ford
    0.78
    boro
    0.78
    Activations Density 0.009%

    No Known Activations