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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16616
    Prev
    Next
    INDEX
    Explanations

    mentions of leadership and being at the forefront of various fields or industries

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating leadership or dominance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.79
     Ezek
    -0.67
    elf
    -0.64
     disemb
    -0.61
     stub
    -0.59
     aired
    -0.59
     Pengu
    -0.58
     vain
    -0.55
     Aires
    -0.55
     flares
    -0.55
    POSITIVE LOGITS
     technologically
    1.00
     academ
    0.95
     innov
    0.89
     financially
    0.84
     economically
    0.84
     athlet
    0.81
     insofar
    0.80
     globally
    0.79
     in
    0.79
     regarding
    0.79
    Activations Density 0.269%

    No Known Activations