© 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. 2-RES-SM
    11. 30401
    Prev
    Next
    INDEX
    Explanations

    trademarks and brand names associated with products

    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
    247
    +0.14
    0.8%
    29
    +0.13
    0.7%
    437
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.14
    0.01
    377
    +0.13
    0.02
    202
    +0.12
    0.01
    Negative Logits
     *"
    -1.49
    erver
    -1.45
    ophil
    -1.44
     conflict
    -1.40
     disturbance
    -1.37
    itor
    -1.32
    omy
    -1.30
    imer
    -1.29
     north
    -1.29
     clashes
    -1.28
    POSITIVE LOGITS
    owing
    1.55
    owed
    1.54
    armed
    1.41
    icles
    1.40
    ificial
    1.38
     Eyes
    1.36
    reads
    1.34
    plicity
    1.31
     ),
    1.31
    nis
    1.29
    Activations Density 0.212%

    No Known Activations