© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22684
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and announcements

    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
    134
    +0.12
    0.7%
    17
    +0.11
    0.6%
    372
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.12
    0.08
    372
    +0.11
    0.01
    51
    +0.11
    0.09
    Negative Logits
    bing
    -1.87
    Reviewer
    -1.64
     jobs
    -1.40
    chat
    -1.39
    bed
    -1.39
    ubot
    -1.38
    etheless
    -1.35
    icultural
    -1.31
    bridge
    -1.31
     “[
    -1.30
    POSITIVE LOGITS
    elta
    1.57
    oyle
    1.48
    uffle
    1.45
    eston
    1.41
     Clause
    1.39
    aland
    1.38
    uple
    1.38
    optera
    1.34
    resse
    1.34
    ords
    1.31
    Activations Density 2.037%

    No Known Activations