© 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. 8326
    Prev
    Next
    INDEX
    Explanations

    phrases introducing personal opinions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion and experiences

    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
     themselves
    -0.97
     yourselves
    -0.71
     oneself
    -0.64
    heny
    -0.60
     economies
    -0.60
    earable
    -0.58
     currents
    -0.57
     kernels
    -0.57
     assail
    -0.57
     ambush
    -0.56
    POSITIVE LOGITS
     personally
    0.79
     myself
    0.67
    ACTED
    0.65
    felt
    0.64
     Wand
    0.63
     happiest
    0.63
    first
    0.62
    azy
    0.61
    writing
    0.60
    å¸
    0.60
    Activations Density 0.313%

    No Known Activations