© 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. 17452
    Prev
    Next
    INDEX
    Explanations

    mentions of elder individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to elderly individuals or the concept of elders

    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
    ï¸ı
    -0.70
    Õ
    -0.68
    Ô
    -0.67
    ores
    -0.66
    atility
    -0.64
    anchester
    -0.64
    ++++++++++++++++
    -0.63
    izable
    -0.63
    ability
    -0.62
    âķIJâķIJ
    -0.62
    POSITIVE LOGITS
     elder
    1.03
    doms
    0.91
    flower
    0.83
     patriarch
    0.78
     brother
    0.76
    ieth
    0.76
     Scrolls
    0.76
     widow
    0.74
    berries
    0.71
     nodd
    0.71
    Activations Density 0.007%

    No Known Activations