© 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. 30621
    Prev
    Next
    INDEX
    Explanations

    negative expressions or sentiments

    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
    59
    +0.13
    0.7%
    215
    +0.12
    0.7%
    42
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.13
    0.10
    471
    +0.12
    0.08
    66
    +0.10
    0.08
    Negative Logits
    "</
    -1.70
    edly
    -1.61
    acular
    -1.56
    ometh
    -1.51
    ulated
    -1.44
     '"
    -1.43
     *"
    -1.42
    noreply
    -1.40
    uously
    -1.37
    ATIONS
    -1.36
    POSITIVE LOGITS
    stable
    1.55
    hess
    1.43
    power
    1.43
    st
    1.36
    alg
    1.36
    hei
    1.35
    Success
    1.35
    tig
    1.34
    etta
    1.34
    rar
    1.33
    Activations Density 0.112%

    No Known Activations