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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 12474
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    pronouns in plural or possessive forms

    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
    ĸļ
    -0.68
    fill
    -0.67
     Walters
    -0.66
    Cu
    -0.66
    Grey
    -0.65
    usa
    -0.65
    mire
    -0.65
    vine
    -0.64
    Sn
    -0.64
    parser
    -0.64
    POSITIVE LOGITS
     own
    1.71
     entire
    1.11
     reputation
    1.01
     fortunes
    1.00
    selves
    0.97
     allegiance
    0.96
     rightful
    0.94
     knees
    0.93
     arms
    0.92
     vision
    0.91
    Activations Density 0.244%

    No Known Activations