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. 11-RES-JB
    6. 8610
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by positive emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to love and its complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.88
    Module
    -0.78
    rax
    -0.78
     Imran
    -0.77
     redund
    -0.76
    uthor
    -0.76
    rm
    -0.75
    ickets
    -0.75
    ulhu
    -0.74
    mins
    -0.74
    POSITIVE LOGITS
     Love
    2.16
    love
    2.01
    Love
    2.00
     love
    1.96
     LOVE
    1.87
     loving
    1.52
     loves
    1.51
     Loving
    1.50
     romance
    1.46
     lover
    1.43
    Activations Density 0.293%

    No Known Activations