© 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. 25656
    Prev
    Next
    INDEX
    Explanations

    expressions of communication or disclosure

    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
    138
    +0.12
    0.6%
    169
    +0.11
    0.6%
    33
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.12
    0.07
    256
    +0.11
    0.07
    250
    +0.11
    0.04
    Negative Logits
    alities
    -1.78
     respectively
    -1.55
    chy
    -1.54
    ancies
    -1.45
     Wrote
    -1.43
    >;
    -1.40
    :$$\
    -1.39
    $$\
    -1.37
     None
    -1.34
     hostage
    -1.33
    POSITIVE LOGITS
    »¿
    2.92
    į
    2.63
    ŀ
    2.57
    Ī
    2.48
    Ł
    2.40
    ı
    2.39
    Ń
    2.39
    ↵
    2.37
    ↵  ³³³
    2.37
    2.37
    Activations Density 0.578%

    No Known Activations