© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    mentions or references to "adult" individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to adulthood and adult-related concepts

    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
    adr
    -0.90
    atility
    -0.76
    ggles
    -0.75
    Ĥİ
    -0.74
    veyard
    -0.74
    ãĤ´ãĥ³
    -0.72
     Cosponsors
    -0.71
    xtap
    -0.71
    SOURCE
    -0.69
    aminer
    -0.68
    POSITIVE LOGITS
    adult
    0.92
    erer
    0.86
    erers
    0.85
     males
    0.84
     adult
    0.83
     male
    0.82
     Swim
    0.80
    hesis
    0.79
    olesc
    0.76
     entertain
    0.72
    Activations Density 0.010%

    No Known Activations