© 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. 25416
    Prev
    Next
    INDEX
    Explanations

    instances of the word "together."

    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
    144
    +0.16
    0.9%
    376
    +0.14
    0.8%
    152
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.16
    0.02
    152
    +0.14
    0.02
    144
    +0.14
    0.01
    Negative Logits
     tolerate
    -1.58
    pite
    -1.54
     tolerated
    -1.47
    ake
    -1.36
    zA
    -1.34
    prof
    -1.34
    taient
    -1.33
     herself
    -1.32
     antibodies
    -1.32
     faint
    -1.30
    POSITIVE LOGITS
    stance
    1.68
    ning
    1.63
    stown
    1.61
    borg
    1.60
    nikov
    1.57
    endor
    1.55
    town
    1.54
    :--
    1.51
    fried
    1.49
    dimension
    1.49
    Activations Density 0.051%

    No Known Activations