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. 7473
    Prev
    Next
    INDEX
    Explanations

    words related to political events or ceremonies

    oai_token-act-pair · gpt-3.5-turbo

    references to presidential inaugurations

    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
    abol
    -0.69
    Interest
    -0.67
    erm
    -0.65
    usc
    -0.65
     Leth
    -0.65
    resp
    -0.64
    Gene
    -0.63
    Tier
    -0.63
    eq
    -0.62
    ective
    -0.62
    POSITIVE LOGITS
    urated
    1.19
    urations
    1.06
     ceremonies
    1.03
     inauguration
    1.02
     ceremony
    0.99
    eering
    0.99
    uration
    0.95
     inaug
    0.89
     festivities
    0.79
    nesday
    0.79
    Activations Density 0.008%

    No Known Activations