© 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. 24759
    Prev
    Next
    INDEX
    Explanations

    specific names and entities relevant to animal welfare and related organizations

    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
    +0.18
    1.0%
    349
    +0.13
    0.7%
    27
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.08
    332
    +0.13
    0.12
    377
    +0.12
    0.08
    Negative Logits
    rooms
    -1.83
    fficients
    -1.63
    breviations
    -1.59
    ings
    -1.55
    theless
    -1.54
    fare
    -1.54
    ções
    -1.49
    notation
    -1.49
    ção
    -1.48
    utta
    -1.47
    POSITIVE LOGITS
    psy
    1.55
     tuberculosis
    1.55
    master
    1.47
     bust
    1.45
     Alzheimer
    1.45
     hostage
    1.42
     depression
    1.42
     AIDS
    1.39
     constant
    1.39
     failure
    1.38
    Activations Density 2.129%

    No Known Activations