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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21672
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to the topic of abortions

    oai_token-act-pair · gpt-3.5-turbo

    references to abortion-related topics and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paran
    -0.93
     Flavoring
    -0.92
     Disneyland
    -0.79
    ãģ®éŃĶ
    -0.77
     Tycoon
    -0.76
     Closed
    -0.76
    MENTS
    -0.75
     Maker
    -0.75
     Crescent
    -0.74
     Pioneer
    -0.74
    POSITIVE LOGITS
    raham
    1.25
    endi
    1.09
    ortion
    1.06
    ilities
    1.05
    dullah
    1.05
    bey
    1.02
    irez
    1.01
    olition
    1.00
    abad
    0.99
    aye
    0.98
    Activations Density 0.005%

    No Known Activations