© 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. 4-RES-SM
    11. 11806
    Prev
    Next
    INDEX
    Explanations

    terms associated with software applications and their functionalities

    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
    90
    +0.12
    0.6%
    83
    +0.10
    0.6%
    418
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.01
    189
    +0.10
    0.03
    90
    +0.10
    0.02
    Negative Logits
    Ļª
    -3.54
    Ĵ
    -3.13
    ¸
    -3.11
    Ĥ¬
    -3.08
    ±
    -3.03
    »¿
    -3.01
    ĻĤ
    -2.92
    Ĭ
    -2.89
    ĥ½
    -2.89
    ↵
    -2.88
    POSITIVE LOGITS
    matically
    1.85
    arily
    1.79
    izable
    1.78
    ization
    1.77
    ized
    1.66
    ally
    1.63
     requiring
    1.61
    zzi
    1.60
     accelerator
    1.58
     server
    1.57
    Activations Density 0.241%

    No Known Activations