© 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 EvalsExportsinterp-engineNEWAPI 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. 26700
    Prev
    Next
    INDEX
    Explanations

    terms related to legal issues and processes

    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
    198
    +0.17
    1.0%
    474
    +0.14
    0.8%
    235
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.17
    0.07
    198
    +0.14
    0.07
    460
    +0.13
    0.06
    Negative Logits
    Ĥ
    -3.60
    »
    -3.30
    <|outofrange|>
    -3.29
    -3.29
    <|outofrange|>
    -3.28
    ↵
    -3.28
    č↵
    -3.28
    ↵
    -3.28
    ↵↵
    -3.28
           ↵
    -3.28
    POSITIVE LOGITS
     Wrestling
    1.66
     Hockey
    1.59
     Films
    1.52
    actory
    1.51
     Edmonton
    1.49
     Eagle
    1.39
     Ath
    1.38
    agan
    1.37
     Assumption
    1.36
     Cookie
    1.36
    Activations Density 0.623%

    No Known Activations