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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 29310
    Prev
    Next
    INDEX
    Explanations

    phrases related to anticipation or waiting

    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
    395
    +0.15
    0.9%
    231
    +0.14
    0.8%
    419
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.15
    0.12
    395
    +0.14
    0.14
    231
    +0.14
    0.12
    Negative Logits
    ĻĤ
    -3.58
    Ļª
    -3.37
    ©
    -2.85
    Īĺ
    -2.79
    ij
    -2.52
    »¿
    -2.49
    ĺ
    -2.41
    Ĥ¬
    -2.37
    Ĩ
    -2.25
    ĭ
    -2.22
    POSITIVE LOGITS
     alike
    2.25
    CASE
    1.57
     thereof
    1.53
    amid
    1.51
    therefore
    1.48
    others
    1.48
    forth
    1.43
     cultures
    1.39
     became
    1.38
     versa
    1.34
    Activations Density 1.819%

    No Known Activations