© 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. 1-RES-JB
    11. 20306
    Prev
    Next
    INDEX
    Explanations

    references to organizations or publications associated with political or societal thoughts and opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words related to the concept of thinking or opinion formation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conservancy
    -0.76
     Adin
    -0.74
    recorded
    -0.70
     clad
    -0.68
    Shipping
    -0.66
    iding
    -0.66
    clad
    -0.65
    Naz
    -0.65
    ipher
    -0.64
    artney
    -0.64
    POSITIVE LOGITS
    ij士
    0.74
    pad
    0.74
     thinkers
    0.69
     think
    0.68
    agram
    0.66
    orial
    0.65
    OTAL
    0.65
    olesterol
    0.65
     impeachment
    0.64
    furt
    0.64
    Activations Density 0.052%

    No Known Activations