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. 8634
    Prev
    Next
    INDEX
    Explanations

    mentions of the state or state-related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "state" in various contexts

    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
    poons
    -0.97
    edin
    -0.84
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    ãĥīãĥ©
    -0.75
    icago
    -0.75
     Aires
    -0.72
     Maw
    -0.72
    bats
    -0.70
    ogle
    -0.69
    sett
    -0.68
    POSITIVE LOGITS
     legislatures
    1.26
     legislature
    1.24
     Legislature
    1.15
     legislator
    1.03
    wide
    1.00
     legislators
    0.98
     governments
    0.92
     Legisl
    0.90
     governors
    0.87
     senate
    0.86
    Activations Density 0.053%

    No Known Activations