© 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. 4-RES-SM
    11. 11638
    Prev
    Next
    INDEX
    Explanations

    terms related to options and selections in contexts of optimization or decision-making

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    271
    +0.13
    0.7%
    66
    +0.13
    0.7%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.13
    0.02
    326
    +0.13
    0.03
    437
    +0.12
    0.03
    Negative Logits
     respect
    -1.83
     NOTICE
    -1.69
     matter
    -1.69
    zzle
    -1.60
     offence
    -1.56
     oath
    -1.50
     responsibility
    -1.46
    ]>
    -1.40
     anniversary
    -1.39
     certainty
    -1.36
    POSITIVE LOGITS
    Ĵ
    4.00
    ↵
    3.93
    <|outofrange|>
    3.93
    ↵            ↵
    3.93
    <|outofrange|>
    3.93
    3.93
    <|outofrange|>
    3.93
    3.93
           ↵
    3.93
    <|outofrange|>
    3.93
    Activations Density 0.264%

    No Known Activations