© 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. 2-MLP-SM
    6. 25758
    Prev
    Next
    INDEX
    Explanations

    terms related to privilege and socioeconomic disparities

    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
    +0.17
    1.0%
    185
    +0.14
    0.8%
    189
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.05
    189
    +0.14
    0.11
    163
    +0.14
    0.00
    Negative Logits
     DISCLAIM
    -1.54
     prospects
    -1.53
     desires
    -1.50
    ypse
    -1.49
    ibles
    -1.46
    nal
    -1.44
    chus
    -1.44
    als
    -1.43
     accomplishments
    -1.42
    CHANTABILITY
    -1.42
    POSITIVE LOGITS
    aging
    1.34
     firstly
    1.33
     normalized
    1.32
     Firstly
    1.32
    oba
    1.26
    opropyl
    1.24
     Emirates
    1.22
     detach
    1.22
     Dutch
    1.22
     Terminal
    1.22
    Activations Density 3.108%

    No Known Activations