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. 5268
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Homer"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "boomer" and its variations, indicating a focus on the Baby Boomer generation

    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
     Assassins
    -0.70
    comings
    -0.65
    orld
    -0.65
    PER
    -0.64
    birth
    -0.64
    CV
    -0.64
    Real
    -0.63
    Ĥª
    -0.63
    nut
    -0.63
    eeds
    -0.63
    POSITIVE LOGITS
    omer
    1.00
    ophone
    0.84
    gdala
    0.80
    ufact
    0.79
    oths
    0.78
    ically
    0.78
    icably
    0.76
    opol
    0.75
    oth
    0.75
    omers
    0.74
    Activations Density 0.012%

    No Known Activations