© 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. 9-RES-JB
    11. 11668
    Prev
    Next
    INDEX
    Explanations

    verbs related to using power or influence over others

    oai_token-act-pair · gpt-3.5-turbo

    references to the use of power and influence among individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.70
    uph
    -0.70
    etsk
    -0.62
    ropolis
    -0.62
    yrinth
    -0.62
    brates
    -0.62
     Sadd
    -0.61
    noon
    -0.61
     Dmit
    -0.60
    nin
    -0.60
    POSITIVE LOGITS
     own
    1.30
     newfound
    1.15
     discretion
    1.10
     clout
    1.08
     expertise
    0.99
     imagination
    0.99
     considerable
    0.97
     fists
    0.92
     knowledge
    0.88
     Own
    0.87
    Activations Density 0.124%

    No Known Activations