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. 5553
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of life and making impacts on lives

    oai_token-act-pair · gpt-3.5-turbo

    references to the impact on people's lives

    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
    CAST
    -0.69
    phabet
    -0.67
    sonian
    -0.67
    ority
    -0.67
    NES
    -0.66
     consolidation
    -0.65
    NESS
    -0.65
    gomery
    -0.63
    AMI
    -0.63
    atchewan
    -0.63
    POSITIVE LOGITS
    chool
    1.03
    ynthesis
    0.97
    pring
    0.84
    lihood
    0.84
    journal
    0.81
    mith
    0.79
    hack
    0.79
    ongs
    0.78
    guard
    0.78
    mares
    0.77
    Activations Density 0.020%

    No Known Activations