© 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. MLP Post
    9. 2-MLP-SM
    11. 25424
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "per" in various contexts, indicating a focus on measurements, ratios, or proportions

    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
    23
    +0.17
    0.9%
    156
    +0.12
    0.7%
    359
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.02
    215
    +0.12
    0.03
    329
    +0.11
    0.01
    Negative Logits
    xmm
    -1.73
    biamo
    -1.71
    umab
    -1.62
    ivo
    -1.57
     memb
    -1.50
     reductase
    -1.49
     stool
    -1.44
    ftware
    -1.42
    sd
    -1.41
    lle
    -1.40
    POSITIVE LOGITS
    Ĺ
    1.44
     ripe
    1.42
    sible
    1.41
     animated
    1.38
     frost
    1.33
     tort
    1.31
     moving
    1.31
    some
    1.31
    ķ
    1.30
     Holt
    1.29
    Activations Density 0.281%

    No Known Activations