© 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. 2416
    Prev
    Next
    INDEX
    Explanations

    instances where the word "this" is used to describe a specific situation or event

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uniqueness or extraordinary 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
    ²¾
    -0.85
    eli
    -0.71
    izen
    -0.71
    orno
    -0.71
    ãĤ·ãĥ£
    -0.69
    ruit
    -0.67
    idel
    -0.67
    izu
    -0.66
    oller
    -0.66
    achus
    -0.65
    POSITIVE LOGITS
     enthusi
    0.87
     kind
    0.83
     crap
    0.81
     stuff
    0.78
     amount
    0.76
     magnitude
    0.74
     egregious
    0.74
     happened
    0.74
     anymore
    0.74
     drastic
    0.73
    Activations Density 0.215%

    No Known Activations