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. 10238
    Prev
    Next
    INDEX
    Explanations

    mentions of the pronoun "they" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to subjects referred to as "they."

    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
     Eleven
    -0.83
    CCC
    -0.81
    cgi
    -0.68
    VW
    -0.66
    paragraph
    -0.66
    ////////////////////////////////
    -0.65
     Cable
    -0.65
     Globe
    -0.65
    CLASSIFIED
    -0.65
    Bull
    -0.64
    POSITIVE LOGITS
    're
    1.29
    've
    1.05
    'll
    1.01
    'd
    0.99
     selves
    0.99
     themselves
    0.86
    selves
    0.85
    ikh
    0.84
     respective
    0.83
    self
    0.79
    Activations Density 0.257%

    No Known Activations