© 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. 12617
    Prev
    Next
    INDEX
    Explanations

    terms related to elderly or aging

    oai_token-act-pair · gpt-3.5-turbo

    references to older individuals and related age dynamics

    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
    utterstock
    -0.79
    odor
    -0.75
    xtap
    -0.75
    atile
    -0.72
    otion
    -0.71
    orial
    -0.70
    Ĥİ
    -0.70
    ple
    -0.70
    cha
    -0.70
    edIn
    -0.68
    POSITIVE LOGITS
     generations
    1.05
     sibling
    1.00
     sister
    0.97
     versions
    0.95
     fashioned
    0.93
     than
    0.90
     brother
    0.87
    owan
    0.81
     Than
    0.81
    than
    0.80
    Activations Density 0.028%

    No Known Activations