© 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. 2-MLP-SM
    11. 23712
    Prev
    Next
    INDEX
    Explanations

    references to education and students

    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
    478
    +0.12
    0.6%
    482
    +0.11
    0.6%
    458
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.12
    0.04
    458
    +0.11
    0.03
    162
    +0.11
    0.04
    Negative Logits
    ians
    -1.76
    lymp
    -1.68
    iens
    -1.54
    writers
    -1.53
    respect
    -1.41
     owners
    -1.40
    Records
    -1.36
    rs
    -1.35
    okers
    -1.34
    makers
    -1.34
    POSITIVE LOGITS
    ī
    1.72
    ulose
    1.50
     NEGLIGENCE
    1.49
    AndroidRuntime
    1.46
    \]](
    1.46
    )|\
    1.42
    "}](#
    1.42
    ¿½
    1.42
     IMPLIED
    1.40
    opian
    1.35
    Activations Density 0.267%

    No Known Activations