© 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. 1-RES-JB
    11. 14284
    Prev
    Next
    INDEX
    Explanations

    references or mentions of individuals in senior positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Senior" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apesh
    -0.73
    tered
    -0.71
    raltar
    -0.70
    ngth
    -0.69
    76561
    -0.69
    igate
    -0.68
    pel
    -0.67
    Ĥİ
    -0.67
    lé
    -0.67
     wrench
    -0.66
    POSITIVE LOGITS
     Senior
    1.11
    Senior
    1.01
     Analyst
    0.92
    IOR
    0.90
    jun
    0.81
    Staff
    0.81
     Staff
    0.80
    iors
    0.78
     Writer
    0.78
     Fellow
    0.77
    Activations Density 0.011%

    No Known Activations