© 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 EvalsExportsAPI 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. 28527
    Prev
    Next
    INDEX
    Explanations

    terms related to retrieval or gaining something back

    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
    410
    +0.15
    0.9%
    467
    +0.15
    0.8%
    111
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    317
    +0.15
    0.01
    200
    +0.14
    0.01
    Negative Logits
     respectively
    -1.60
     resisting
    -1.54
     sparing
    -1.43
     fixing
    -1.43
    scribe
    -1.36
     sometime
    -1.36
     restoring
    -1.35
     attracting
    -1.33
    ]>
    -1.32
     suppressing
    -1.31
    POSITIVE LOGITS
    ĻĤ
    2.78
    Ĵ
    2.24
    ¡
    2.03
    ĸ
    2.00
    ½
    1.99
    ¢
    1.98
    ĥ½
    1.93
    ±
    1.90
    ª
    1.89
    Ģ
    1.88
    Activations Density 0.013%

    No Known Activations