© 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. 2-RES-SM
    11. 10109
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and regulatory frameworks

    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
    186
    +0.16
    0.9%
    76
    +0.14
    0.8%
    231
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.38
    156
    +0.14
    0.37
    71
    +0.14
    0.35
    Negative Logits
    ĥ½
    -2.17
    ¦
    -2.11
    £
    -1.84
    Ļ
    -1.79
    \]](
    -1.78
    ®
    -1.75
    ·¸
    -1.72
    -1.69
    ↵↵
    -1.69
    ↵
    -1.69
    POSITIVE LOGITS
     yet
    1.65
    backs
    1.51
    ivers
    1.38
    ó
    1.37
    yet
    1.37
    ){#
    1.34
     victories
    1.32
     victory
    1.31
    ires
    1.30
     gains
    1.29
    Activations Density 4.617%

    No Known Activations