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. 4-RES-JB
    6. 12715
    Prev
    Next
    INDEX
    Explanations

    pronouns and their related actions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns referring to groups or entities in various contexts

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

    No Comments

    Negative Logits
     Christy
    -0.75
     Cards
    -0.72
     Unreal
    -0.71
     Nex
    -0.71
     Grape
    -0.68
    -->
    -0.63
     Bless
    -0.63
    aii
    -0.62
     âī
    -0.62
     Rusty
    -0.61
    POSITIVE LOGITS
     relates
    0.81
     matured
    0.80
     progresses
    0.79
     progressed
    0.78
     grows
    0.77
     approached
    0.76
     realised
    0.75
     transitioned
    0.75
     prepares
    0.74
     pond
    0.74
    Activations Density 0.157%

    No Known Activations