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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15361
    Prev
    Next
    INDEX
    Explanations

    words related to competitiveness

    oai_token-act-pair · gpt-3.5-turbo

    references to competition and competitiveness

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

    No Comments

    Negative Logits
    hung
    -0.83
    gur
    -0.75
    stones
    -0.72
    slave
    -0.71
    FORE
    -0.70
    pez
    -0.69
    stanbul
    -0.69
    ANG
    -0.69
    DonaldTrump
    -0.68
    qt
    -0.68
    POSITIVE LOGITS
     minded
    0.92
    ly
    0.91
     multiplayer
    0.86
     advantages
    0.86
     juices
    0.85
     Advantage
    0.82
    eers
    0.81
     pressures
    0.80
     newsp
    0.79
    ized
    0.79
    Activations Density 0.012%

    No Known Activations