© 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. 0-RES-JB
    11. 5282
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and automation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of automation and its impact on society and jobs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autom
    -0.83
     appet
    -0.77
     neglig
    -0.76
     trophies
    -0.74
     Fam
    -0.73
     Garg
    -0.72
     trophy
    -0.69
     inst
    -0.69
    riors
    -0.69
     Foss
    -0.69
    POSITIVE LOGITS
    Bridge
    2.17
     automation
    1.89
    ensen
    1.36
    Cat
    1.19
     storms
    1.17
    Mat
    1.12
    CAP
    0.89
    Balt
    0.87
    Zone
    0.86
     Verse
    0.83
    Activations Density 0.042%

    No Known Activations