© 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. 3618
    Prev
    Next
    INDEX
    Explanations

    words related to demagogy or demeaning actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to democracy and democratic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    WAYS
    -0.74
     Elves
    -0.73
    worms
    -0.64
    lihood
    -0.62
    tis
    -0.62
     flares
    -0.62
     Abyss
    -0.62
     supper
    -0.62
     flared
    -0.62
    ties
    -0.62
    POSITIVE LOGITS
    agogue
    1.21
    ographically
    1.13
    agog
    1.12
    ilit
    1.12
    onym
    1.11
    aterial
    1.08
    olition
    1.05
    otion
    1.05
    ploy
    1.05
    otions
    1.01
    Activations Density 0.016%

    No Known Activations