© 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. 30139
    Prev
    Next
    INDEX
    Explanations

    terms related to quantities and classifications

    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
    156
    +0.34
    2.0%
    17
    +0.15
    0.9%
    285
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.34
    0.08
    12
    +0.15
    0.07
    499
    +0.14
    0.05
    Negative Logits
    ľĵ
    -4.61
    -4.08
    ↵↵
    -4.08
    -4.08
             ↵
    -4.08
    <|outofrange|>
    -4.08
    -4.08
    <|outofrange|>
    -4.08
    -4.08
    ↵
    -4.08
    POSITIVE LOGITS
     equals
    1.62
     cycle
    1.60
     including
    1.57
     corresponds
    1.57
     except
    1.51
     individually
    1.45
     knows
    1.42
     includes
    1.39
     volume
    1.36
     consists
    1.35
    Activations Density 0.999%

    No Known Activations