© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25347
    Prev
    Next
    INDEX
    Explanations

    mentions of various facilities and organizations, particularly those related to community services or healthcare

    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
    23
    +0.14
    0.8%
    289
    +0.14
    0.8%
    306
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.14
    0.04
    306
    +0.14
    0.03
    289
    +0.13
    0.03
    Negative Logits
     Rev
    -1.54
    lite
    -1.53
    bud
    -1.50
    quez
    -1.47
     Series
    -1.46
    OPS
    -1.45
    orts
    -1.44
    ocur
    -1.43
    sheet
    -1.41
    pl
    -1.39
    POSITIVE LOGITS
     oneself
    1.79
     madness
    1.64
     disbelief
    1.61
    acity
    1.58
     yourself
    1.54
     mercy
    1.53
     annoyance
    1.52
     inclination
    1.51
    jective
    1.51
     surprise
    1.51
    Activations Density 0.223%

    No Known Activations