© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15047
    Prev
    Next
    INDEX
    Explanations

    terms related to authority, control, or influence

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of powers, particularly in a governmental or influential context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rette
    -0.72
    yard
    -0.66
    jar
    -0.66
    live
    -0.66
    addle
    -0.65
    che
    -0.64
    Äį
    -0.63
    Hispanic
    -0.63
    icker
    -0.62
    lier
    -0.61
    POSITIVE LOGITS
     powers
    3.95
    powers
    2.64
     Powers
    2.64
     power
    1.79
     abilities
    1.67
    power
    1.50
     superpower
    1.42
     faculties
    1.40
    Power
    1.30
     Power
    1.30
    Activations Density 0.012%

    No Known Activations