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

    Neuronpedia

    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. 7-RES-JB
    11. 10867
    Prev
    Next
    INDEX
    Explanations

    words related to the process of appointing or being appointed to a position or role

    oai_token-act-pair · gpt-3.5-turbo

    references to appointments and appointees in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    patch
    -0.86
    Ïģ
    -0.78
    λ
    -0.77
    psc
    -0.73
    00007
    -0.71
    pack
    -0.70
    pling
    -0.69
    jer
    -0.68
    iday
    -0.67
    ι
    -0.66
    POSITIVE LOGITS
    ees
    0.97
     appointments
    0.97
     appoint
    0.88
    ments
    0.87
    ointed
    0.85
     ineligible
    0.84
     appointment
    0.84
    eering
    0.82
     appointed
    0.80
    ancies
    0.79
    Activations Density 0.037%

    No Known Activations