© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 2709
    Prev
    Next
    INDEX
    Explanations

    words related to authoritarianism, dictatorship, control, and eradication

    oai_token-act-pair · gpt-3.5-turbo

    themes related to oppression and hierarchy

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

    No Comments

    Negative Logits
    FACE
    -0.77
    manship
    -0.73
    hyde
    -0.72
    SHIP
    -0.70
     Suit
    -0.67
     Keeper
    -0.67
     Stevens
    -0.66
     Door
    -0.64
     Solitaire
    -0.64
     Clause
    -0.64
    POSITIVE LOGITS
    ined
    1.12
    oved
    1.11
    arant
    1.08
    icably
    1.06
    otions
    1.05
    ixed
    1.04
    otion
    1.03
    ittance
    1.01
    ained
    1.01
    astically
    1.01
    Activations Density 0.014%

    No Known Activations