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

    Neuronpedia

    APICircuit 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. 4401
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular female individual

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the pronoun "her."

    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
    Process
    -0.57
    rahim
    -0.56
    ivo
    -0.55
    gaard
    -0.54
    DX
    -0.54
    otation
    -0.54
    rencies
    -0.54
    lite
    -0.54
    çīĪ
    -0.53
    agos
    -0.53
    POSITIVE LOGITS
     her
    3.09
     hers
    2.57
     herself
    2.50
    Her
    2.14
     she
    2.02
    She
    1.94
     HER
    1.90
     Her
    1.81
    she
    1.76
     She
    1.74
    Activations Density 0.097%

    No Known Activations