© 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. MLP Post
    9. 2-MLP-SM
    11. 23906
    Prev
    Next
    INDEX
    Explanations

    actions related to turning electronic devices on and off

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    443
    +0.10
    0.6%
    261
    +0.10
    0.5%
    454
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    454
    +0.10
    0.01
    299
    +0.10
    0.02
    214
    +0.10
    0.04
    Negative Logits
    ks
    -1.66
    ijn
    -1.38
    argin
    -1.33
    \])]{}
    -1.26
    ification
    -1.26
    ters
    -1.25
     crossings
    -1.24
    ](#
    -1.21
    forms
    -1.19
    form
    -1.19
    POSITIVE LOGITS
    isely
    1.67
    eville
    1.55
    '."
    1.47
    ĨĴ
    1.44
    anese
    1.41
    itud
    1.41
    hetti
    1.40
    ·¸
    1.40
     lots
    1.39
     Thank
    1.38
    Activations Density 0.920%

    No Known Activations