© 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. 9836
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition or rivalry

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaining or losing ground in competitive contexts

    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
    ãĥŁ
    -0.65
     gul
    -0.65
     Loft
    -0.63
    rafted
    -0.61
     Bucket
    -0.59
    obyl
    -0.59
    ammad
    -0.58
     Esk
    -0.58
     Bild
    -0.58
     ut
    -0.58
    POSITIVE LOGITS
     against
    0.95
     nationally
    0.89
     among
    0.85
     advantage
    0.85
     amongst
    0.83
     economically
    0.79
     financially
    0.76
     favoring
    0.76
     atop
    0.75
     advantages
    0.74
    Activations Density 0.186%

    No Known Activations