© 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. 8655
    Prev
    Next
    INDEX
    Explanations

    different types of brands, business names, and software/tools

    oai_token-act-pair · gpt-3.5-turbo

    key names and terms associated with various brands, tools, or organizational structures

    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
     subclass
    -0.55
     Aval
    -0.54
     shortage
    -0.54
     Fallout
    -0.54
     whistleblower
    -0.52
     misconception
    -0.51
     AND
    -0.51
     fallacy
    -0.49
     omission
    -0.49
     sore
    -0.49
    POSITIVE LOGITS
     alike
    0.97
     respectively
    0.80
     thereof
    0.79
     versa
    0.73
    osh
    0.70
    oliath
    0.69
     thereto
    0.67
    az
    0.65
    aza
    0.65
    oultry
    0.64
    Activations Density 0.555%

    No Known Activations