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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-SM
    11. 28054
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in various statements

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    412
    +0.18
    1.0%
    87
    +0.15
    0.8%
    250
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.18
    0.07
    111
    +0.15
    0.06
    271
    +0.14
    0.02
    Negative Logits
    ·¸
    -3.94
    ĻĤ
    -3.84
    -3.79
    ↵
    -3.79
       ↵
    -3.79
    <|outofrange|>
    -3.79
    č↵
    -3.79
    <|outofrange|>
    -3.79
    -3.79
    -3.79
    POSITIVE LOGITS
     unlocked
    1.58
     augmented
    1.52
     restored
    1.36
     abandoned
    1.35
     endings
    1.35
    ancel
    1.34
     tightened
    1.33
    NG
    1.29
     perpet
    1.27
    iances
    1.26
    Activations Density 0.402%

    No Known Activations