© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6758
    Prev
    Next
    INDEX
    Explanations

    mentions of individual entities or actions related to policies, health care, and legal mandates

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "individual" and its related terms

    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
     Dame
    -0.87
    lands
    -0.79
    ync
    -0.68
     Twice
    -0.68
    UV
    -0.68
     Deadly
    -0.67
    KO
    -0.66
     Neighbor
    -0.65
     Lethal
    -0.63
    word
    -0.63
    POSITIVE LOGITS
    individual
    1.10
    ividual
    1.07
     individual
    1.05
     identifiable
    0.97
    isations
    0.86
    itarian
    0.86
    istic
    0.86
     individuals
    0.84
    istically
    0.83
     participant
    0.82
    Activations Density 0.013%

    No Known Activations