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. 9-RES-JB
    6. 21908
    Prev
    Next
    INDEX
    Explanations

    pronouns 'who' or 'they'

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" as a subject in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.63
     Anything
    -0.63
     Nova
    -0.63
    SE
    -0.63
    å½
    -0.63
     bruising
    -0.59
     Basics
    -0.59
    VIS
    -0.58
    Untitled
    -0.58
     Affordable
    -0.58
    POSITIVE LOGITS
    upon
    1.22
     promptly
    1.00
     incidentally
    0.94
     nevertheless
    0.92
     presumably
    0.90
     thankfully
    0.90
     nonetheless
    0.87
     understandably
    0.86
    oped
    0.85
     subsequently
    0.85
    Activations Density 0.145%

    No Known Activations