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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23613
    Prev
    Next
    INDEX
    Explanations

    terms addressing audiences in a formal setting

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "ladies" and "gentlemen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ds
    -0.79
    osta
    -0.70
    yrus
    -0.68
    onis
    -0.68
    aya
    -0.67
    ython
    -0.67
    icted
    -0.66
    Emb
    -0.65
    sequence
    -0.65
    aeda
    -0.65
    POSITIVE LOGITS
     gentlemen
    0.89
    maid
    0.85
     gentleman
    0.83
    utenant
    0.77
    men
    0.75
    woman
    0.75
    owship
    0.75
     Gaga
    0.74
    bugs
    0.72
     Toast
    0.70
    Activations Density 0.015%

    No Known Activations