© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2850
    Prev
    Next
    INDEX
    Explanations

    references to funding related to Planned Parenthood and discussions about abortion laws

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to funding and controversial issues surrounding Planned Parenthood and abortion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Admir
    -0.95
    Tang
    -0.93
     Dhabi
    -0.85
    sbm
    -0.82
    leon
    -0.82
     Monaco
    -0.81
     Chess
    -0.80
    uckland
    -0.79
     Wembley
    -0.78
     Albion
    -0.78
    POSITIVE LOGITS
     abortions
    2.14
     abortion
    2.14
     Planned
    2.07
    abortion
    1.96
     Abortion
    1.93
     pregnancy
    1.75
     Parenthood
    1.71
     contraception
    1.70
     reproductive
    1.70
     contraceptive
    1.68
    Activations Density 0.331%

    No Known Activations