© 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 EvalsExportsinterp-engineNEWAPI 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. 23557
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate and property features

    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
    +0.15
    0.9%
    381
    +0.15
    0.9%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.15
    0.09
    14
    +0.15
    0.13
    404
    +0.14
    0.09
    Negative Logits
    ovir
    -1.55
    bies
    -1.51
    ours
    -1.49
     logo
    -1.47
     yourself
    -1.45
    antage
    -1.45
    heit
    -1.44
    ças
    -1.43
    missibility
    -1.42
     licenses
    -1.37
    POSITIVE LOGITS
     embarrassed
    1.90
     terrified
    1.70
     violated
    1.68
     scared
    1.68
     shocked
    1.67
     furious
    1.57
     ashamed
    1.55
    ppen
    1.53
     devastated
    1.50
    night
    1.50
    Activations Density 2.728%

    No Known Activations