© 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. 0-MLP-SM
    11. 25623
    Prev
    Next
    INDEX
    Explanations

    mentions of "ig" or similar sounding patterns within a context related to food or ingredients

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.14
    0.8%
    115
    +0.11
    0.6%
    454
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    454
    +0.14
    0.03
    27
    +0.11
    0.02
    356
    +0.11
    0.03
    Negative Logits
    ´
    -2.25
    µ
    -2.19
    ĭ
    -2.17
    ¡
    -2.12
    ĸ´
    -2.11
    ¼
    -2.10
    ·¸
    -2.00
    ¶
    -1.95
    Ĥ
    -1.94
    Ĭ
    -1.94
    POSITIVE LOGITS
    iosity
    1.62
    rams
    1.51
    ORY
    1.41
    archy
    1.39
     argc
    1.37
     baggage
    1.35
    RET
    1.33
     ecosystem
    1.32
    aceae
    1.32
     opportunity
    1.31
    Activations Density 0.060%

    No Known Activations