© 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. 3-RES-JB
    11. 22271
    Prev
    Next
    INDEX
    Explanations

    words related to competitive events or contests

    oai_token-act-pair · gpt-3.5-turbo

    mentions of competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ths
    -0.78
    stones
    -0.76
    config
    -0.73
    thus
    -0.70
    erest
    -0.67
    then
    -0.64
    haul
    -0.64
    vest
    -0.63
    stead
    -0.63
    rich
    -0.62
    POSITIVE LOGITS
     competition
    0.82
     entrants
    0.74
    itism
    0.74
    igslist
    0.72
    vernment
    0.70
    ivity
    0.70
    eers
    0.70
     examinations
    0.70
     exams
    0.70
     competitions
    0.69
    Activations Density 0.015%

    No Known Activations