© 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. 4-RES-JB
    11. 13504
    Prev
    Next
    INDEX
    Explanations

    phrases related to elderly individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to seniors and retirees

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

    No Comments

    Negative Logits
    orious
    -0.81
    alter
    -0.72
    rawdownloadcloneembedreportprint
    -0.70
    orie
    -0.70
    ²¾
    -0.69
    efully
    -0.66
    orical
    -0.65
    arms
    -0.63
    te
    -0.63
    axe
    -0.62
    POSITIVE LOGITS
    iors
    0.78
    CRIP
    0.77
    escent
    0.76
    opausal
    0.76
     Living
    0.75
    men
    0.74
     citiz
    0.73
    folk
    0.73
    berries
    0.72
    cript
    0.71
    Activations Density 0.012%

    No Known Activations