Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29535
    Prev
    Next
    INDEX
    Explanations

    terms related to taxes, tax benefits, and tax legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    263
    +0.21
    1.2%
    419
    +0.18
    1.1%
    186
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.21
    0.14
    263
    +0.18
    0.15
    354
    +0.15
    0.10
    Negative Logits
    ħ
    -1.50
     counterparts
    -1.43
    Ļª
    -1.42
     /**
    -1.39
     rebut
    -1.35
     secular
    -1.32
    ttes
    -1.31
     closet
    -1.30
    ĻĤ
    -1.27
     MORE
    -1.26
    POSITIVE LOGITS
    wagen
    1.71
    vere
    1.64
     lacked
    1.50
    ights
    1.50
    ever
    1.50
    iness
    1.46
    ophore
    1.45
    ract
    1.44
     recogn
    1.43
    ession
    1.41
    Activations Density 3.268%

    No Known Activations