© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26778
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of numerical data or statistics

    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
    407
    +0.14
    0.8%
    416
    +0.13
    0.7%
    31
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.14
    0.10
    310
    +0.13
    0.06
    404
    +0.13
    0.07
    Negative Logits
    Ł
    -3.00
    ª
    -2.65
    ±
    -2.49
    ħ
    -2.47
    Ĥ¬
    -2.45
    ĸ
    -2.41
    IJ
    -2.40
    ĥ½
    -2.27
    ķ
    -2.23
    º
    -2.19
    POSITIVE LOGITS
     promise
    1.82
    keywords
    1.44
    ourier
    1.44
    pub
    1.43
    probe
    1.41
    kowski
    1.40
    iation
    1.40
    icip
    1.36
    uum
    1.36
    cerpt
    1.36
    Activations Density 1.547%

    No Known Activations