© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    mentions of education, being educated, or educating others

    oai_token-act-pair · gpt-3.5-turbo
    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
    imposed
    -0.64
    apan
    -0.64
    ity
    -0.63
     launcher
    -0.60
    ettes
    -0.60
     dimension
    -0.59
    apa
    -0.59
    dimension
    -0.58
     containment
    -0.58
    hedral
    -0.57
    POSITIVE LOGITS
     guesses
    0.94
    liter
    0.83
    otle
    0.81
    eering
    0.77
    ourgeois
    0.77
    llor
    0.77
    renheit
    0.75
    ĨĴ
    0.74
    habi
    0.73
    irect
    0.70
    Activations Density 0.052%

    No Known Activations