© 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. 6-RES-JB
    11. 11963
    Prev
    Next
    INDEX
    Explanations

    words related to competition or being considered for a position, often as a top candidate

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitive standing or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iencies
    -0.79
    arching
    -0.75
    erie
    -0.72
    tein
    -0.71
    arb
    -0.69
    isan
    -0.68
    romy
    -0.68
    orgetown
    -0.66
    arton
    -0.66
    ijk
    -0.66
    POSITIVE LOGITS
     contender
    1.15
     contenders
    1.05
     contestant
    0.90
     competitor
    0.86
     contestants
    0.85
     frontrunner
    0.84
     challengers
    0.81
     newcomer
    0.74
     vying
    0.73
     Reborn
    0.72
    Activations Density 0.033%

    No Known Activations