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. 3-RES-JB
    6. 18911
    Prev
    Next
    INDEX
    Explanations

    words related to "home" and activities or items associated with it

    oai_token-act-pair · gpt-3.5-turbo

    references to "home" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andum
    -0.72
    uality
    -0.70
     McKenna
    -0.67
    OTUS
    -0.65
     Twain
    -0.64
    ounty
    -0.64
    uel
    -0.64
     Delta
    -0.64
    =-=-=-=-=-=-=-=-
    -0.62
    usha
    -0.62
    POSITIVE LOGITS
    coming
    0.96
    chool
    0.88
    home
    0.85
    brew
    0.85
    buy
    0.83
    grown
    0.81
    pun
    0.80
    opath
    0.79
    owners
    0.77
    nikov
    0.77
    Activations Density 0.041%

    No Known Activations