© 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. 14788
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to equality across 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
    271
    +0.18
    1.0%
    21
    +0.16
    0.9%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.18
    0.01
    470
    +0.16
    0.02
    203
    +0.12
    0.01
    Negative Logits
    ://
    -1.87
    smen
    -1.82
    fulness
    -1.75
    ning
    -1.63
    hos
    -1.59
    sters
    -1.56
    hole
    -1.56
    ware
    -1.55
    ÅĦ
    -1.54
    mary
    -1.53
    POSITIVE LOGITS
    IJ
    4.44
    ĥ
    4.34
    ¤
    4.31
    ĸ
    4.29
    ģ
    4.28
    Ī
    4.25
    Ģ
    4.22
    ħ
    4.21
    ¨
    4.18
    į
    4.16
    Activations Density 0.149%

    No Known Activations