© 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. 23377
    Prev
    Next
    INDEX
    Explanations

    the word "where" in various contexts

    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
    176
    +0.12
    0.6%
    169
    +0.11
    0.6%
    310
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    190
    +0.12
    0.05
    380
    +0.11
    0.04
    302
    +0.10
    0.05
    Negative Logits
    ħ
    -2.15
    ģ
    -1.65
    ļ
    -1.61
    Ľ
    -1.50
    ı
    -1.50
    bie
    -1.50
    istically
    -1.42
    GAN
    -1.39
     guess
    -1.33
    °
    -1.33
    POSITIVE LOGITS
    éd
    1.68
    arynge
    1.61
    ennis
    1.54
    xit
    1.50
    icorn
    1.50
    haul
    1.46
    cher
    1.44
    atus
    1.42
    ussels
    1.41
    itt
    1.40
    Activations Density 0.322%

    No Known Activations