© 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. 0-RES-JB
    6. 12100
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "abortions"

    oai_token-act-pair · gpt-3.5-turbo

    references to the topic of abortions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cue
    -0.84
     outfit
    -0.67
    alan
    -0.66
     package
    -0.65
    pect
    -0.65
     digital
    -0.65
     challenge
    -0.65
     competitor
    -0.64
     task
    -0.64
     asset
    -0.64
    POSITIVE LOGITS
     abortions
    3.35
     births
    2.12
     marriages
    1.94
     pregnancies
    1.90
     executions
    1.59
     miscar
    1.57
     weddings
    1.51
     rapes
    1.49
     suicides
    1.39
     surgeries
    1.38
    Activations Density 0.029%

    No Known Activations