© 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. 0-MLP-SM
    11. 28014
    Prev
    Next
    INDEX
    Explanations

    references to the concept of character 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
    336
    +0.12
    0.7%
    156
    +0.11
    0.6%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    336
    +0.12
    0.01
    277
    +0.11
    0.01
    40
    +0.11
    0.01
    Negative Logits
    ¸
    -3.45
    ·¸
    -3.44
    ³
    -3.39
    ĥ½
    -3.31
    Ĺ
    -3.30
    į
    -3.29
    IJ
    -3.21
    ĭ
    -3.19
    ´
    -3.15
    ¬
    -3.00
    POSITIVE LOGITS
    istic
    2.06
    istically
    1.94
    istics
    1.84
    bridge
    1.79
    stown
    1.78
    hattan
    1.74
    pile
    1.73
    arters
    1.71
    arily
    1.70
    smen
    1.68
    Activations Density 0.011%

    No Known Activations