© 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. 11352
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making 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
    365
    +0.18
    1.0%
    66
    +0.13
    0.7%
    172
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.18
    0.05
    365
    +0.13
    0.04
    66
    +0.11
    0.04
    Negative Logits
    ľĵ
    -2.98
    Ľ
    -2.79
    »¿
    -2.78
    ĥ½
    -2.64
    Ł
    -2.55
    ľ
    -2.53
    Į
    -2.48
    ¿½
    -2.48
    ·¸
    -2.39
    ¾
    -2.39
    POSITIVE LOGITS
    ality
    2.16
    al
    1.92
     maker
    1.67
    making
    1.65
    table
    1.61
     reached
    1.59
    gement
    1.57
    iser
    1.54
     path
    1.53
    gment
    1.51
    Activations Density 0.249%

    No Known Activations