© 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. 28202
    Prev
    Next
    INDEX
    Explanations

    specific references to geographical or physical locations

    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
    87
    +0.13
    0.7%
    212
    +0.13
    0.7%
    415
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.13
    0.04
    30
    +0.13
    0.05
    497
    +0.12
    0.05
    Negative Logits
    zos
    -1.55
    onium
    -1.48
    ius
    -1.44
    eth
    -1.40
    lic
    -1.39
    lion
    -1.38
    ed
    -1.38
     ordered
    -1.35
    doms
    -1.35
    ially
    -1.34
    POSITIVE LOGITS
    agem
    1.40
    imester
    1.36
    orrow
    1.30
     gaps
    1.28
     Food
    1.28
     että
    1.27
     gap
    1.26
     strand
    1.26
    ige
    1.25
    arser
    1.25
    Activations Density 0.062%

    No Known Activations