© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11270
    Prev
    Next
    INDEX
    Explanations

    words related to assuming roles or positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to assuming roles or responsibilities

    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
    vine
    -0.72
     Scores
    -0.68
    ivers
    -0.65
     refunds
    -0.65
    veland
    -0.63
     smugglers
    -0.63
    apa
    -0.61
    rays
    -0.61
    flix
    -0.60
     contrace
    -0.60
    POSITIVE LOGITS
     role
    1.63
     position
    1.49
     roles
    1.48
     duties
    1.46
     responsibilities
    1.42
     mantle
    1.37
     helm
    1.36
     throne
    1.35
     positions
    1.33
     responsibility
    1.27
    Activations Density 0.354%

    No Known Activations