© 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. 2-RES-SM
    11. 13777
    Prev
    Next
    INDEX
    Explanations

    terminology related to development and improvement processes

    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
    246
    +0.14
    0.8%
    392
    +0.12
    0.7%
    365
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.14
    0.03
    327
    +0.12
    0.03
    344
    +0.12
    0.03
    Negative Logits
    unnumbered
    -1.78
    еÑģк
    -1.47
    Ļª
    -1.42
    wic
    -1.40
     neg
    -1.39
    anza
    -1.38
    UTERS
    -1.36
     dass
    -1.36
    tek
    -1.36
    mina
    -1.33
    POSITIVE LOGITS
    ally
    1.98
    ères
    1.97
     into
    1.88
    ifically
    1.88
    ively
    1.82
    entials
    1.78
    urally
    1.76
    etically
    1.71
     projects
    1.68
     enough
    1.67
    Activations Density 0.091%

    No Known Activations