© 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. 2-RES-SM
    11. 11071
    Prev
    Next
    INDEX
    Explanations

    choices and options related to selection and customization

    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
    +0.16
    0.9%
    17
    +0.15
    0.8%
    285
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.16
    0.08
    17
    +0.15
    -0.01
    300
    +0.14
    0.06
    Negative Logits
    ·
    -2.80
    º
    -2.69
    į
    -2.69
    ĻĤ
    -2.68
    §
    -2.66
    °
    -2.66
    ľ
    -2.65
    ĸ
    -2.58
    Ķ
    -2.53
    ²
    -2.52
    POSITIVE LOGITS
     wisely
    1.74
     criteria
    1.50
     please
    1.45
     randomized
    1.40
     prizes
    1.37
    choose
    1.35
     randomly
    1.34
     genre
    1.33
     vain
    1.33
     chart
    1.32
    Activations Density 2.223%

    No Known Activations