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. 11435
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition and rivalries across various contexts

    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
    156
    +0.18
    1.1%
    300
    +0.13
    0.8%
    169
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.18
    0.02
    300
    +0.13
    0.02
    186
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.37
    ´
    -2.31
    ³
    -2.13
    º
    -2.10
    ±
    -2.08
    ĻĤ
    -2.07
    ĨĴ
    -2.06
    İ
    -1.98
    ľ
    -1.83
    IJ
    -1.80
    POSITIVE LOGITS
    pole
    1.80
    inction
    1.69
    etition
    1.63
     competition
    1.58
    oon
    1.55
     bidding
    1.54
    isation
    1.54
    card
    1.50
    ockey
    1.45
    eer
    1.44
    Activations Density 0.293%

    No Known Activations