© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26250
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers and numerical values

    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
    376
    +0.14
    0.8%
    115
    +0.13
    0.7%
    209
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.14
    0.07
    53
    +0.13
    0.06
    4
    +0.12
    0.06
    Negative Logits
    hin
    -1.70
    www
    -1.64
    laughter
    -1.58
     ours
    -1.51
     backdrop
    -1.44
    gov
    -1.43
     sense
    -1.39
     meaning
    -1.34
     myself
    -1.30
     responsibility
    -1.30
    POSITIVE LOGITS
    £
    3.36
    Ļ
    3.20
    ª
    3.20
    Į
    3.13
    ĥ
    2.96
    ģ
    2.93
    ł
    2.93
    Ľ
    2.89
    ħ
    2.88
    ¬
    2.86
    Activations Density 5.724%

    No Known Activations