© 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 EvalsExportsAPI 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. 13146
    Prev
    Next
    INDEX
    Explanations

    words related to various types of devices or technology references

    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
    +0.14
    0.8%
    17
    +0.13
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.14
    0.06
    32
    +0.13
    0.05
    121
    +0.12
    0.05
    Negative Logits
    ferent
    -1.64
    atase
    -1.61
    mental
    -1.53
     himself
    -1.53
    ément
    -1.53
    worm
    -1.53
    cip
    -1.49
    ction
    -1.45
    ctor
    -1.44
    ment
    -1.42
    POSITIVE LOGITS
    £
    2.83
    ĺ
    2.76
    ª
    2.66
    ŀ
    2.63
    Ĵ
    2.58
    ½
    2.51
    «
    2.50
    Ļ
    2.48
    ı
    2.46
    į
    2.45
    Activations Density 0.149%

    No Known Activations