© 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. 26461
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "on" 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/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
    407
    +0.11
    0.6%
    46
    +0.11
    0.6%
    166
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.11
    0.21
    152
    +0.11
    0.17
    47
    +0.11
    0.14
    Negative Logits
    oint
    -1.69
     decomposition
    -1.56
     syll
    -1.48
     exceptions
    -1.41
    REL
    -1.36
     /**<
    -1.35
     ceil
    -1.33
     Owner
    -1.33
     Bin
    -1.32
    apis
    -1.31
    POSITIVE LOGITS
    ģ
    2.51
    Ļª
    2.39
    ĭ
    2.20
    ¸
    2.19
    ²
    2.13
    Ĭ
    2.13
    ±
    2.07
    İ
    2.03
    ħ
    2.03
    fitting
    1.96
    Activations Density 0.629%

    No Known Activations