© 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. 10-RES-JB
    11. 24295
    Prev
    Next
    INDEX
    Explanations

    phrases related to seniority and ranking in organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to high-ranking officials and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Syndrome
    -0.70
    Unique
    -0.70
    rums
    -0.69
    issors
    -0.68
    oute
    -0.68
    photos
    -0.67
    avia
    -0.66
     Cookies
    -0.65
    crow
    -0.63
    ournals
    -0.63
    POSITIVE LOGITS
     adviser
    1.16
     aide
    1.16
     officials
    1.08
     aides
    1.06
     official
    1.04
     bureaucr
    1.04
     advisor
    1.03
     diplomat
    1.02
     executives
    1.00
     staffer
    0.99
    Activations Density 0.101%

    No Known Activations