© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29840
    Prev
    Next
    INDEX
    Explanations

    specific names of characters or individuals associated with entertainment and gaming 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.15
    0.9%
    23
    +0.15
    0.8%
    179
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.15
    -0.01
    23
    +0.15
    0.13
    507
    +0.12
    0.04
    Negative Logits
    ĸ
    -2.21
    ĻĤ
    -2.09
    ģ
    -1.98
    Ģ
    -1.95
    į
    -1.90
    ¬
    -1.87
    Ħ
    -1.83
    Ĥ¬
    -1.78
    Ĵ
    -1.77
    ĥ½
    -1.76
    POSITIVE LOGITS
    cil
    1.61
    wered
    1.60
     softer
    1.52
    ]>
    1.48
    =”
    1.45
     calf
    1.40
     promise
    1.37
     shorter
    1.37
     taller
    1.33
     ’
    1.33
    Activations Density 3.559%

    No Known Activations