© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24373
    Prev
    Next
    INDEX
    Explanations

    phrases related to escalating emotions and tensions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating concern or rising tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specifications
    -0.76
    illac
    -0.76
     prototypes
    -0.68
     rewritten
    -0.64
    guide
    -0.63
     slots
    -0.62
     Copy
    -0.62
     customized
    -0.61
    itures
    -0.61
     waterways
    -0.60
    POSITIVE LOGITS
     palpable
    0.99
     aroused
    0.89
    terness
    0.86
     contagious
    0.84
     disbelief
    0.81
     ferv
    0.79
     simmer
    0.77
     gripped
    0.77
     tempered
    0.77
     expressed
    0.77
    Activations Density 0.549%

    No Known Activations