© 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. 0-RES-JB
    11. 13984
    Prev
    Next
    INDEX
    Explanations

    names related to women

    oai_token-act-pair · gpt-3.5-turbo

    references to an individual, particularly in contexts involving personal relationships and connections

    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
     shootout
    -0.69
    otation
    -0.69
     tail
    -0.61
     shutdown
    -0.60
     sectors
    -0.59
     working
    -0.59
     conditioning
    -0.59
     driving
    -0.59
     dunk
    -0.59
     noise
    -0.57
    POSITIVE LOGITS
    Her
    3.54
     Her
    2.29
    She
    2.16
    her
    1.77
     HER
    1.74
    HER
    1.69
    she
    1.52
     her
    1.51
     She
    1.47
     herself
    1.37
    Activations Density 0.009%

    No Known Activations