© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    mentions of layoffs

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of layoffs, especially in relation to different contexts or subjects

    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
    atorial
    -0.93
    atory
    -0.81
    GV
    -0.81
     captcha
    -0.71
    Balt
    -0.71
     superpower
    -0.71
    atories
    -0.68
    ator
    -0.68
    ators
    -0.67
     fer
    -0.66
    POSITIVE LOGITS
     Lay
    3.86
    Lay
    3.28
    lay
    1.61
     lay
    1.60
     Slay
    1.30
     lays
    1.12
     laying
    1.11
     Stretch
    1.10
     Alley
    1.09
     laid
    1.06
    Activations Density 0.025%

    No Known Activations