© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28071
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and reflections

    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
    274
    +0.16
    0.9%
    419
    +0.14
    0.9%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.16
    0.21
    390
    +0.14
    0.08
    255
    +0.13
    0.15
    Negative Logits
    ¾
    -2.25
    ĥ
    -2.22
    º
    -2.09
    ¿
    -2.05
    Ŀ
    -2.03
    ħ
    -2.03
    Ĺ
    -2.03
    ŀ
    -1.98
    ¯
    -1.98
    ļ
    -1.96
    POSITIVE LOGITS
    MOESM
    1.46
     Conclusion
    1.44
    ences
    1.42
    **:
    1.42
    Conclusion
    1.42
    idenote
    1.41
    ************************
    1.41
    oche
    1.39
    :**
    1.35
    blogger
    1.33
    Activations Density 5.469%

    No Known Activations