© 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. 2452
    Prev
    Next
    INDEX
    Explanations

    words related to growth or increase

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a rising prevalence or trend

    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
     Mub
    -0.79
    atography
    -0.77
    toe
    -0.76
    mates
    -0.75
    printed
    -0.75
    bley
    -0.75
    ère
    -0.74
    breaker
    -0.74
    oops
    -0.73
    aine
    -0.72
    POSITIVE LOGITS
     pains
    1.19
     trend
    1.06
     impat
    1.05
     realization
    1.03
     discontent
    1.00
     dissatisfaction
    1.00
     popularity
    0.98
     frustration
    0.95
     tide
    0.91
     demand
    0.89
    Activations Density 0.063%

    No Known Activations