© 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. 0-MLP-SM
    6. 26956
    Prev
    Next
    INDEX
    Explanations

    references to additional items or ideas

    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
    457
    +0.15
    0.8%
    255
    +0.13
    0.7%
    303
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.44
    209
    +0.13
    0.28
    402
    +0.12
    0.26
    Negative Logits
    ij
    -3.00
    §
    -3.00
    ı
    -2.97
    Ģ
    -2.91
    Īĺ
    -2.90
    ŀ
    -2.89
    Ŀ
    -2.86
    Ľ
    -2.85
    »¿
    -2.83
    <|outofrange|>
    -2.80
    POSITIVE LOGITS
    ocur
    1.56
    ridges
    1.54
    prototype
    1.52
    nai
    1.52
    áĥ
    1.50
    iles
    1.45
    ิ
    1.44
    course
    1.43
     whom
    1.41
    plate
    1.40
    Activations Density 1.595%

    No Known Activations