© 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. 4-RES-SM
    11. 10374
    Prev
    Next
    INDEX
    Explanations

    issues related to performance and effectiveness in various contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    320
    +0.13
    0.7%
    167
    +0.12
    0.7%
    474
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.08
    320
    +0.12
    0.10
    83
    +0.12
    0.08
    Negative Logits
    ¦
    -4.25
    ģ
    -4.17
    ¢
    -4.03
    Ħ
    -4.02
    »¿
    -3.93
    Ļª
    -3.85
    č↵č↵
    -3.72
       ↵
    -3.72
    č↵
    -3.72
    -3.72
    POSITIVE LOGITS
     insufficient
    2.89
     nonetheless
    2.80
     nevertheless
    2.58
     lacking
    2.54
     nowhere
    2.52
     unable
    2.47
     still
    2.44
     unclear
    2.36
     inadequate
    2.34
     lacks
    2.32
    Activations Density 1.429%

    No Known Activations