© 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. 11-RES-JB
    11. 7740
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority, power, and legal actions being taken

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental authority and military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Topic
    -0.81
    ription
    -0.64
    iddled
    -0.62
    roma
    -0.62
     mention
    -0.61
     PTS
    -0.61
     birthday
    -0.60
    tk
    -0.60
     Wedding
    -0.59
    blogspot
    -0.59
    POSITIVE LOGITS
     resources
    1.31
     levers
    1.20
     firepower
    1.14
     energies
    1.09
     tools
    1.06
     ingenuity
    1.06
     capacities
    1.05
     manpower
    1.02
    available
    1.01
     capabilities
    1.00
    Activations Density 0.319%

    No Known Activations