© 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. 8-RES-JB
    11. 7746
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth or change

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to economic growth and trends

    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
     oath
    -0.77
     etiquette
    -0.76
     jurors
    -0.74
    hol
    -0.70
     clutter
    -0.69
     wording
    -0.67
    gery
    -0.66
    names
    -0.66
     incrim
    -0.65
     jerseys
    -0.65
    POSITIVE LOGITS
     exponential
    1.17
     accelerating
    0.99
    celer
    0.99
     accelerate
    0.96
     stagn
    0.96
     accelerated
    0.96
    growth
    0.96
     rapid
    0.92
     stalled
    0.91
     leaps
    0.88
    Activations Density 0.510%

    No Known Activations