© 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. 10840
    Prev
    Next
    INDEX
    Explanations

    references to weeks and weekly events

    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
    337
    +0.12
    0.7%
    477
    +0.12
    0.7%
    41
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.12
    0.04
    163
    +0.12
    0.02
    297
    +0.11
    0.04
    Negative Logits
    Ĵ
    -3.64
    Ŀ
    -3.38
    Ń
    -3.24
    ľĵ
    -3.24
    ĸ
    -3.20
    §
    -3.16
    ↵↵
    -3.08
    -3.08
           ↵
    -3.08
    ↵
    -3.08
    POSITIVE LOGITS
    lies
    2.21
    end
    2.13
    enden
    2.10
    day
    2.08
    night
    2.00
    mare
    1.93
    long
    1.92
    ends
    1.83
    lin
    1.79
    ending
    1.79
    Activations Density 0.127%

    No Known Activations