© 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. 7-RES-JB
    11. 23134
    Prev
    Next
    INDEX
    Explanations

    verbs related to life and existence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of living

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.86
    ippi
    -0.80
    ession
    -0.74
    reg
    -0.72
    ery
    -0.71
    enei
    -0.69
    essee
    -0.68
    elight
    -0.68
    pex
    -0.66
    intendent
    -0.65
    POSITIVE LOGITS
    lihood
    1.04
     vic
    0.96
     happily
    0.81
    liness
    0.75
     comfortably
    0.75
     Forever
    0.74
    stead
    0.74
    uate
    0.73
     peacefully
    0.72
     dangerously
    0.72
    Activations Density 0.036%

    No Known Activations