© 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. 0-MLP-SM
    6. 27849
    Prev
    Next
    INDEX
    Explanations

    the year 2008

    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
    494
    +0.14
    0.8%
    51
    +0.13
    0.7%
    238
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.14
    0.03
    508
    +0.13
    0.03
    51
    +0.12
    0.02
    Negative Logits
    ĥ
    -1.64
    Ļ
    -1.55
     liberty
    -1.51
     commission
    -1.50
     rule
    -1.48
     suspicion
    -1.46
    İ
    -1.44
     comment
    -1.43
     sect
    -1.43
     yes
    -1.41
    POSITIVE LOGITS
    icolor
    2.12
    dot
    1.79
    –
    1.76
    afx
    1.72
    culus
    1.72
    ÅĽÄĩ
    1.68
    #{$
    1.64
    ienn
    1.64
    itable
    1.61
    borne
    1.50
    Activations Density 0.015%

    No Known Activations