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. 24282
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically related to politics or news events

    oai_token-act-pair · gpt-3.5-turbo

    references to Washington, D.C

    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
    order
    -0.73
    unct
    -0.68
    ordering
    -0.66
    fund
    -0.66
    gger
    -0.65
    odic
    -0.65
    other
    -0.64
    eworld
    -0.64
    hist
    -0.64
    lass
    -0.63
    POSITIVE LOGITS
    ASHINGTON
    1.29
    WASHINGTON
    1.18
    aukee
    1.11
    ashtra
    0.91
    Washington
    0.88
     DC
    0.87
    sburgh
    0.85
    ADA
    0.85
     STATE
    0.85
    ukong
    0.85
    Activations Density 0.006%

    No Known Activations