© 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. 1-RES-SM
    11. 27309
    Prev
    Next
    INDEX
    Explanations

    actions involving decision-making and evaluations

    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
    45
    +0.14
    0.8%
    292
    +0.12
    0.6%
    431
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.14
    0.06
    429
    +0.12
    0.04
    4
    +0.11
    0.04
    Negative Logits
    ĨĴ
    -4.22
    <|outofrange|>
    -3.53
    ↵
    -3.53
           ↵
    -3.53
    -3.53
    -3.53
    ↵  ↵
    -3.53
    -3.53
    -3.53
    -3.53
    POSITIVE LOGITS
    InstanceState
    1.40
     Galois
    1.38
    ricanes
    1.37
    ftware
    1.35
    pired
    1.35
    ld
    1.35
    GIN
    1.34
    pires
    1.34
     Redistributions
    1.34
    pire
    1.33
    Activations Density 0.882%

    No Known Activations