© 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. 30306
    Prev
    Next
    INDEX
    Explanations

    references to future opportunities or possibilities

    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
    140
    +0.13
    0.7%
    289
    +0.12
    0.7%
    16
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.13
    0.01
    140
    +0.12
    0.01
    16
    +0.12
    0.01
    Negative Logits
    Į
    -1.84
    yna
    -1.58
    Lew
    -1.46
     overtime
    -1.40
    Marie
    -1.40
     urgency
    -1.35
     Acad
    -1.32
    arman
    -1.32
     mourn
    -1.31
    rish
    -1.27
    POSITIVE LOGITS
    holes
    1.85
    ground
    1.81
    hole
    1.78
    us
    1.72
    fire
    1.60
    uses
    1.59
    agem
    1.50
    position
    1.47
    ivities
    1.47
    vier
    1.46
    Activations Density 0.015%

    No Known Activations