Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24201
    Prev
    Next
    INDEX
    Explanations

    female pronouns, especially 'She' in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "She"

    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
    ynski
    -0.65
    VEN
    -0.57
    IRE
    -0.57
    ppelin
    -0.57
    IDS
    -0.54
    GAME
    -0.54
    oÄŁ
    -0.53
    BIP
    -0.51
    ATCH
    -0.51
    SPONSORED
    -0.51
    POSITIVE LOGITS
     She
    3.19
    She
    2.62
    she
    2.37
     Her
    2.17
     SHE
    2.12
     she
    1.92
    Her
    1.80
     herself
    1.62
     her
    1.53
     He
    1.45
    Activations Density 0.023%

    No Known Activations