© 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. 29681
    Prev
    Next
    INDEX
    Explanations

    the term "Tar" 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
    369
    +0.19
    1.1%
    2
    +0.14
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.19
    0.01
    385
    +0.14
    0.01
    327
    +0.12
    0.01
    Negative Logits
     hers
    -1.56
     invention
    -1.55
    ÑĢоÑģ
    -1.51
    tig
    -1.45
     com
    -1.43
    ERTYPE
    -1.43
    ção
    -1.42
    unctional
    -1.42
    t
    -1.37
    ferentially
    -1.37
    POSITIVE LOGITS
    iffs
    1.73
    heads
    1.69
    fonts
    1.61
    boro
    1.61
     rpm
    1.60
    ifa
    1.58
    iff
    1.56
    ains
    1.56
    vised
    1.54
    aine
    1.53
    Activations Density 0.012%

    No Known Activations