© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 12395
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional distress and reactions to external pressures

    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
    56
    +0.18
    1.0%
    215
    +0.13
    0.7%
    6
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.18
    0.11
    406
    +0.13
    0.13
    480
    +0.13
    0.11
    Negative Logits
    ķ
    -1.86
    arily
    -1.71
     reached
    -1.70
    Ŀ
    -1.62
    Ĩ
    -1.58
    Ģ
    -1.58
    Īĺ
    -1.46
    ably
    -1.46
    utively
    -1.43
    Mac
    -1.39
    POSITIVE LOGITS
     blame
    1.54
     vengeance
    1.53
     habit
    1.53
     accusations
    1.46
    ypse
    1.46
     wrongdoing
    1.44
    charg
    1.44
     reputation
    1.44
    uities
    1.42
    ductive
    1.39
    Activations Density 2.346%

    No Known Activations