© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27214
    Prev
    Next
    INDEX
    Explanations

    the expression of preference or liking

    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
    486
    +0.11
    0.6%
    197
    +0.11
    0.6%
    274
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.11
    0.09
    197
    +0.11
    0.09
    486
    +0.11
    0.09
    Negative Logits
    rvert
    -1.62
    odor
    -1.40
     ..."
    -1.38
    irl
    -1.36
    iced
    -1.35
     **_
    -1.35
    Newton
    -1.35
    oby
    -1.34
     romance
    -1.34
    Introduction
    -1.34
    POSITIVE LOGITS
    ĥ½
    3.71
    °
    3.34
    ĸ´
    3.28
    Į
    3.25
    ¼
    3.19
    ½
    3.04
              ↵
    2.99
    ↵
    2.99
    2.99
    ↵
    2.99
    Activations Density 0.590%

    No Known Activations