© 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. 2-RES-JB
    11. 1612
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional fulfillment or completion

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating emotional voids or gaps in life experiences

    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
    NetMessage
    -0.85
    Featured
    -0.74
     NG
    -0.71
    ption
    -0.70
     Artist
    -0.65
    Artist
    -0.64
     Scrolls
    -0.64
    UGH
    -0.64
    meier
    -0.62
     Cheong
    -0.62
    POSITIVE LOGITS
    ulus
    0.77
    lite
    0.74
     Unleashed
    0.73
    angel
    0.70
     eleph
    0.70
    ropolis
    0.68
     exponent
    0.67
     equals
    0.65
    friends
    0.65
    href
    0.65
    Activations Density 0.000%

    No Known Activations