© 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. 1-RES-JB
    11. 10469
    Prev
    Next
    INDEX
    Explanations

    words related to leadership or positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    mentions of leadership roles and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nee
    -0.77
     Gund
    -0.76
     Oo
    -0.75
    Ô
    -0.74
     Mel
    -0.74
     Coulter
    -0.71
    ISS
    -0.71
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.71
     incidentally
    -0.68
     McA
    -0.67
    POSITIVE LOGITS
     leadership
    1.21
    leaders
    0.98
    jriwal
    0.90
    cius
    0.88
    ahime
    0.86
    wcs
    0.85
     leader
    0.84
     strugg
    0.84
    emouth
    0.84
     referen
    0.83
    Activations Density 0.014%

    No Known Activations