© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12486
    Prev
    Next
    INDEX
    Explanations

    terminology related to technology and programming instructions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.20
    1.2%
    47
    +0.15
    0.9%
    271
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    88
    +0.20
    0.13
    492
    +0.15
    0.10
    95
    +0.14
    0.11
    Negative Logits
    ¿½
    -1.81
    ¾
    -1.67
    ableness
    -1.62
    liness
    -1.59
     respects
    -1.57
    unnumbered
    -1.44
     admission
    -1.41
     Economy
    -1.35
     competence
    -1.35
     deference
    -1.32
    POSITIVE LOGITS
    á̬
    1.57
    áĢº
    1.52
    wordpress
    1.43
    à³
    1.43
    ='
    1.41
    "}](#
    1.40
    á̝
    1.37
    à¯
    1.36
    ilent
    1.30
    osomes
    1.28
    Activations Density 5.869%

    No Known Activations