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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4822
    Prev
    Next
    INDEX
    Explanations

    words related to authority, control, and influence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of power and its various implications in different contexts

    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
     Von
    -0.77
    lov
    -0.75
     Taste
    -0.72
    ALK
    -0.71
    riad
    -0.70
    romeda
    -0.69
    eryl
    -0.68
    verett
    -0.68
    dk
    -0.67
    aro
    -0.65
    POSITIVE LOGITS
     levers
    1.03
     vested
    1.02
    FUL
    0.85
    houses
    0.84
    lessness
    0.83
     conferred
    0.83
     outage
    0.83
     wielded
    0.80
     powerless
    0.80
     delegated
    0.80
    Activations Density 0.035%

    No Known Activations