© 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. 11-RES-JB
    11. 15015
    Prev
    Next
    INDEX
    Explanations

    female character names in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    references to female characters and their actions or roles in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Female Descriptors

    No Comments

    Negative Logits
    catentry
    -0.86
    actionDate
    -0.78
    Downloadha
    -0.76
    codes
    -0.70
    Writing
    -0.69
    indal
    -0.68
    Copyright
    -0.65
    acters
    -0.64
     endorsements
    -0.60
    Reviewer
    -0.59
    POSITIVE LOGITS
     glared
    1.53
     glanced
    1.52
     sighed
    1.52
     nodded
    1.51
     stared
    1.48
     grinned
    1.46
     frowned
    1.45
     blinked
    1.44
     smiled
    1.43
     chuckled
    1.38
    Activations Density 0.181%

    No Known Activations