© 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. 2-RES-JB
    6. 18635
    Prev
    Next
    INDEX
    Explanations

    mentions about human beings, especially in a philosophical or reflective context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "human beings."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LINE
    -0.72
    REP
    -0.69
    BALL
    -0.69
    DEP
    -0.68
    Els
    -0.67
     Jub
    -0.67
    INTER
    -0.67
    UMP
    -0.67
    NRS
    -0.66
    KC
    -0.66
    POSITIVE LOGITS
     beings
    1.11
    terness
    0.98
     inhab
    0.90
    rity
    0.88
    iuses
    0.84
    aurus
    0.83
     endowed
    0.80
    chwitz
    0.80
     sacrificed
    0.78
    brates
    0.78
    Activations Density 0.014%

    No Known Activations