© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12999
    Prev
    Next
    INDEX
    Explanations

    phrases related to income and its relationship to fertility rates

    oai_token-act-pair · gpt-3.5-turbo

    references to fertility and its socio-economic implications

    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
    inness
    -0.88
    Priv
    -0.75
    rawdownloadcloneembedreportprint
    -0.74
    Journal
    -0.73
    alg
    -0.72
    inez
    -0.71
    Lear
    -0.71
    href
    -0.70
    upon
    -0.69
    alone
    -0.69
    POSITIVE LOGITS
     fertility
    0.99
    ertility
    0.80
     infertility
    0.76
     hormone
    0.75
     mell
    0.73
    amental
    0.72
     fert
    0.71
    roid
    0.69
    icide
    0.69
    liction
    0.69
    Activations Density 0.012%

    No Known Activations