© 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. 27008
    Prev
    Next
    INDEX
    Explanations

    expressions or phrases that indicate mathematical operations or calculations

    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
    164
    +0.12
    0.7%
    251
    +0.11
    0.7%
    177
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.12
    0.01
    253
    +0.11
    0.01
    164
    +0.10
    0.01
    Negative Logits
    ubot
    -1.67
    abad
    -1.47
    taient
    -1.45
     authorities
    -1.44
     luck
    -1.43
     consulted
    -1.41
    ipore
    -1.40
    cit
    -1.38
    istan
    -1.38
    isation
    -1.35
    POSITIVE LOGITS
    Ĥ¬
    1.88
    IJ
    1.86
    ij
    1.77
    Ī
    1.70
    {-
    1.67
    ĨĴ
    1.67
    Ĭ
    1.65
    ±
    1.61
    ¦
    1.61
    Ħ
    1.58
    Activations Density 0.074%

    No Known Activations