© 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. 27793
    Prev
    Next
    INDEX
    Explanations

    reference to intensity levels in various contexts

    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
    156
    +0.18
    1.1%
    376
    +0.14
    0.8%
    497
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.18
    0.01
    497
    +0.14
    0.01
    179
    +0.13
    0.01
    Negative Logits
    ções
    -1.69
     fortune
    -1.58
     happier
    -1.55
    Ĥ
    -1.49
    ±
    -1.46
     abandon
    -1.44
    ¼
    -1.44
     conject
    -1.44
    ção
    -1.43
     unconscious
    -1.42
    POSITIVE LOGITS
    ily
    1.72
    frame
    1.72
    chart
    1.67
    charts
    1.66
    RT
    1.58
    isp
    1.58
    uly
    1.55
    ICU
    1.54
    IMAGE
    1.51
    CT
    1.50
    Activations Density 0.006%

    No Known Activations