© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 10930
    Prev
    Next
    INDEX
    Explanations

    phrases involving numerical comparisons and thresholds

    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
    115
    +0.13
    0.7%
    136
    +0.12
    0.7%
    267
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.04
    267
    +0.12
    0.03
    284
    +0.11
    0.04
    Negative Logits
    Management
    -1.61
    >&
    -1.49
    reviewed
    -1.49
    ock
    -1.46
    omes
    -1.42
    EM
    -1.41
     pretty
    -1.41
    OST
    -1.40
    Summary
    -1.40
    ARCH
    -1.39
    POSITIVE LOGITS
    ĥ½
    2.75
    »¿
    2.51
    ľ
    2.41
    ī
    2.32
    Ĥ¬
    2.23
    ĥ
    2.16
              ↵ 
    2.13
                                                 
    2.13
    ↵        ↵       
    2.13
    ↵↵           
    2.13
    Activations Density 0.233%

    No Known Activations