© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    keywords related to work and care

    oai_token-act-pair · gpt-3.5-turbo

    mentions of work and care-related activities or responsibilities

    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
     disappearing
    -0.73
     circling
    -0.65
     popping
    -0.64
     flo
    -0.62
     ruining
    -0.61
     turning
    -0.60
     Newsp
    -0.60
     collapsing
    -0.60
     seizing
    -0.60
     headlines
    -0.59
    POSITIVE LOGITS
    uate
    0.90
    dress
    0.88
    ociate
    0.88
    enance
    0.82
    itate
    0.78
    ative
    0.76
     efficiently
    0.76
    aintain
    0.75
     properly
    0.75
     adequately
    0.75
    Activations Density 0.246%

    No Known Activations