© 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. 6-RES-JB
    11. 18374
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a threat or impending danger

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impending threats or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verts
    -0.86
    ials
    -0.83
    rosse
    -0.81
    portion
    -0.80
    xy
    -0.80
    tes
    -0.80
    alion
    -0.79
    %]
    -0.76
    girl
    -0.75
    bits
    -0.75
    POSITIVE LOGITS
     doom
    1.15
     looming
    1.00
     omin
    0.97
     looms
    0.85
     threat
    0.82
     inev
    0.82
     deadlines
    0.79
     catastrophe
    0.79
     imminent
    0.78
     instability
    0.77
    Activations Density 0.052%

    No Known Activations