© 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. 29138
    Prev
    Next
    INDEX
    Explanations

    references to iPhone models

    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
    195
    +0.13
    0.8%
    182
    +0.11
    0.6%
    94
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.13
    0.02
    94
    +0.11
    0.02
    93
    +0.11
    0.02
    Negative Logits
    ¯
    -2.70
    ĭ
    -2.66
    «
    -2.48
    ¿
    -2.38
    ¼
    -2.37
    ĺ
    -2.36
    ½
    -2.28
    §
    -2.23
    Ł
    -2.23
    -2.16
    POSITIVE LOGITS
    SEC
    1.67
    itals
    1.56
    cles
    1.56
    stalk
    1.54
    wood
    1.52
    ium
    1.52
    stem
    1.51
     quarters
    1.49
    chitz
    1.46
    volt
    1.45
    Activations Density 0.024%

    No Known Activations