© 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. 26450
    Prev
    Next
    INDEX
    Explanations

    terms related to acquisition or gaining something

    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
    369
    +0.16
    0.9%
    2
    +0.15
    0.9%
    388
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.16
    0.02
    2
    +0.15
    0.02
    343
    +0.14
    0.02
    Negative Logits
    Ķ
    -2.27
    Ĺ
    -2.21
    ĸ´
    -2.17
    Ļ
    -2.08
     else
    -2.03
     ↵
    -2.02
    č↵
    -2.02
    ↵
    -2.02
    <|outofrange|>
    -2.02
    <|outofrange|>
    -2.02
    POSITIVE LOGITS
    oustic
    2.22
    ryl
    1.98
    quisition
    1.90
    nex
    1.80
    ropolis
    1.78
    ribe
    1.74
    quired
    1.72
    ube
    1.71
    claim
    1.70
    hern
    1.70
    Activations Density 0.049%

    No Known Activations