© 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. 31136
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

    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
    482
    +0.12
    0.7%
    478
    +0.12
    0.7%
    115
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.12
    0.02
    288
    +0.12
    0.04
    136
    +0.11
    -0.00
    Negative Logits
     Declaration
    -1.71
    --
    -1.70
    \]](
    -1.59
    Competing
    -1.54
     lists
    -1.53
    OST
    -1.51
    SEC
    -1.46
    IVE
    -1.39
    shall
    -1.36
    uild
    -1.36
    POSITIVE LOGITS
    ī
    4.68
    ´
    4.52
    ¬
    4.49
    ¯
    4.47
    ¶
    4.40
    Ī
    4.35
    Īĺ
    4.34
    ¾
    4.34
    ¦
    4.30
    ®
    4.28
    Activations Density 0.135%

    No Known Activations