© 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. 0-MLP-SM
    11. 27979
    Prev
    Next
    INDEX
    Explanations

    the concept of removable features or components in various contexts

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    156
    +0.25
    1.5%
    376
    +0.14
    0.8%
    148
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.25
    0.01
    340
    +0.14
    0.01
    24
    +0.13
    0.01
    Negative Logits
     slightest
    -1.72
    ighter
    -1.48
     sweat
    -1.44
    unts
    -1.41
    aliana
    -1.38
    OW
    -1.36
    documentclass
    -1.31
     queer
    -1.31
    ĥ½
    -1.27
     fierce
    -1.26
    POSITIVE LOGITS
    "}](#
    1.50
    ités
    1.48
    itious
    1.46
    apat
    1.45
    pose
    1.43
     domains
    1.41
    limits
    1.37
    pool
    1.36
     regarding
    1.36
    iors
    1.36
    Activations Density 1.561%

    No Known Activations