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. 2-RES-JB
    6. 3573
    Prev
    Next
    INDEX
    Explanations

    references to common household items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to households and household-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.88
    */(
    -0.85
    Downloadha
    -0.85
    psey
    -0.80
    heimer
    -0.78
    acebook
    -0.77
     Amon
    -0.75
    ktop
    -0.75
    pez
    -0.71
    terday
    -0.70
    POSITIVE LOGITS
     household
    0.84
     pets
    0.83
    ry
    0.80
    ãĤ©
    0.78
     incomes
    0.78
    mates
    0.78
     appliances
    0.76
     chores
    0.71
     cleaners
    0.70
     income
    0.70
    Activations Density 0.009%

    No Known Activations