© 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. 8-RES-JB
    11. 6538
    Prev
    Next
    INDEX
    Explanations

    mentions of the term 'abortion'

    oai_token-act-pair · gpt-3.5-turbo

    references to abortion and related regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -1.31
     guiActiveUnfocused
    -0.89
    âĵĺ
    -0.78
     Riy
    -0.73
    hew
    -0.73
    Ear
    -0.73
    urat
    -0.70
    inguished
    -0.69
    lime
    -0.68
    UME
    -0.68
    POSITIVE LOGITS
     abortion
    0.95
     pills
    0.91
     abortions
    0.90
     clinics
    0.88
     clinic
    0.86
     Parenthood
    0.85
     rights
    0.84
    abortion
    0.84
     pregnancy
    0.83
     termination
    0.80
    Activations Density 0.035%

    No Known Activations