© 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. 9-RES-JB
    11. 9961
    Prev
    Next
    INDEX
    Explanations

    references to authoritative figures or leaders

    oai_token-act-pair · gpt-3.5-turbo

    the term "boss" used in various contexts, often related to authority or leadership

    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
     Pwr
    -0.78
     Scotia
    -0.78
    CAST
    -0.66
     Lauder
    -0.65
    ctica
    -0.64
     Trails
    -0.64
     CTR
    -0.63
    selves
    -0.61
    lihood
    -0.61
     Verge
    -0.60
    POSITIVE LOGITS
    anova
    0.90
    olean
    0.90
    ulas
    0.87
    es
    0.87
    enger
    0.85
    hips
    0.85
    nuts
    0.82
    enthal
    0.82
    enhagen
    0.81
    heet
    0.81
    Activations Density 0.033%

    No Known Activations