© 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. 4-RES-JB
    11. 10640
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Juggernaut" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    words related to "Jugg" and variations, often referring to a character or a theme associated with juggling

    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
    ĺħ
    -0.82
    £ı
    -0.79
    ngth
    -0.77
     lapse
    -0.72
    piece
    -0.71
     gaze
    -0.66
     obser
    -0.65
     superficial
    -0.65
     Desire
    -0.64
    ŃĶ
    -0.64
    POSITIVE LOGITS
    ernaut
    1.44
    ugg
    1.06
    aneers
    1.02
    itives
    0.97
    glers
    0.91
    atto
    0.88
    aroo
    0.88
    estones
    0.87
    abulary
    0.87
    enda
    0.86
    Activations Density 0.006%

    No Known Activations