© 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. 8511
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions and problems

    oai_token-act-pair · gpt-3.5-turbo

    issues related to societal challenges and emotional states

    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
    ITNESS
    -0.77
    ETHOD
    -0.70
     kosher
    -0.62
     Qual
    -0.61
     Koran
    -0.61
     Psal
    -0.60
     Athe
    -0.59
    urches
    -0.57
     prelim
    -0.57
    fed
    -0.57
    POSITIVE LOGITS
     altogether
    0.88
     wherever
    0.88
     plag
    0.88
     peacefully
    0.76
     ASAP
    0.71
     caused
    0.70
    naire
    0.68
     arising
    0.68
     prevalent
    0.68
     efficiently
    0.67
    Activations Density 0.601%

    No Known Activations