© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to tumultuous or challenging experiences or situations

    oai_token-act-pair · gpt-3.5-turbo

    metaphors related to journeys and 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
    ofer
    -0.73
    */(
    -0.72
    elled
    -0.71
    orks
    -0.69
    license
    -0.69
    issan
    -0.67
    vae
    -0.67
    itte
    -0.67
    ocular
    -0.67
    available
    -0.66
    POSITIVE LOGITS
     ordeal
    1.07
     saga
    0.95
     tragedy
    0.89
     whirlwind
    0.88
     tumultuous
    0.87
     harrowing
    0.85
     excruciating
    0.82
     fraught
    0.82
     slog
    0.81
     inaction
    0.81
    Activations Density 0.604%

    No Known Activations