© 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
    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. 17209
    Prev
    Next
    INDEX
    Explanations

    phrases related to female individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, focusing on their actions and attributes

    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
    ype
    -0.91
    ypes
    -0.91
    kefeller
    -0.87
    ornia
    -0.86
    inctions
    -0.70
    brush
    -0.69
    arios
    -0.69
    VERTIS
    -0.67
    ENSE
    -0.66
    ozy
    -0.66
    POSITIVE LOGITS
     husband
    1.35
    ding
    1.34
    metic
    1.23
    cule
    1.19
     herself
    1.16
     daughter
    1.08
    ded
    1.07
    nia
    1.05
     boyfriend
    1.03
     Majesty
    1.01
    Activations Density 0.118%

    No Known Activations