© 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. 24256
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or permission

    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
    297
    +0.12
    0.7%
    358
    +0.11
    0.6%
    20
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.12
    0.05
    130
    +0.11
    0.04
    88
    +0.10
    0.02
    Negative Logits
     enemies
    -1.69
     welcome
    -1.55
     xe
    -1.44
     hearts
    -1.40
    ually
    -1.38
     root
    -1.37
     glad
    -1.36
     heart
    -1.34
     character
    -1.34
     comfort
    -1.32
    POSITIVE LOGITS
    lickr
    2.00
    park
    1.68
    wagen
    1.59
    enda
    1.59
    erk
    1.56
    erta
    1.56
    camp
    1.50
    ionale
    1.49
    usiness
    1.47
    levard
    1.47
    Activations Density 0.104%

    No Known Activations