© 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. 1-RES-SM
    6. 27084
    Prev
    Next
    INDEX
    Explanations

    terms related to associations and relational structures

    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
    0
    +0.12
    0.7%
    376
    +0.12
    0.7%
    417
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.12
    0.01
    0
    +0.12
    0.01
    283
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -2.12
    ¸
    -2.10
    ´
    -2.08
    »
    -2.05
    ¯
    -2.04
    º
    -2.04
    <|outofrange|>
    -1.94
                                                      
    -1.94
    <|outofrange|>
    -1.94
    ↵↵↵     
    -1.94
    POSITIVE LOGITS
     SIG
    1.62
    inib
    1.48
    arily
    1.46
    CLC
    1.45
    ivity
    1.43
    innati
    1.43
    rients
    1.42
     arte
    1.41
    ible
    1.39
     peaks
    1.38
    Activations Density 0.047%

    No Known Activations