© 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. 2-MLP-SM
    11. 24560
    Prev
    Next
    INDEX
    Explanations

    terms related to travel and customer service experiences

    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
    156
    +0.26
    1.5%
    150
    +0.13
    0.8%
    422
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.26
    0.09
    261
    +0.13
    -0.01
    50
    +0.12
    0.02
    Negative Logits
     trailing
    -1.61
    astically
    -1.42
    've
    -1.42
    fully
    -1.41
    ail
    -1.33
    ÅĽÄĩ
    -1.33
    matically
    -1.32
    leading
    -1.32
    soon
    -1.30
     unders
    -1.27
    POSITIVE LOGITS
    ancies
    1.47
     instance
    1.45
     workshops
    1.44
    ancy
    1.34
     hearings
    1.33
    ois
    1.31
     licenses
    1.31
     Workshop
    1.29
     classes
    1.28
     experiments
    1.28
    Activations Density 3.809%

    No Known Activations