© 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. 8-RES-JB
    11. 3173
    Prev
    Next
    INDEX
    Explanations

    descriptions of political plans and strategies

    oai_token-act-pair · gpt-3.5-turbo

    references to political plans and proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iably
    -0.78
    ewitness
    -0.75
     Laugh
    -0.70
    Db
    -0.69
     accidental
    -0.67
    Sensor
    -0.67
     Takeru
    -0.64
     contam
    -0.64
    aunder
    -0.63
     downed
    -0.63
    POSITIVE LOGITS
     roadmap
    1.34
     proposals
    1.22
     outline
    1.22
     blueprint
    1.21
     overhaul
    1.17
     outlining
    1.15
     outlined
    1.14
     outlines
    1.13
     manifesto
    1.08
     revisions
    1.07
    Activations Density 0.729%

    No Known Activations