© 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. 26893
    Prev
    Next
    INDEX
    Explanations

    numeric values and related structures

    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
    1
    +0.16
    0.9%
    100
    +0.12
    0.7%
    345
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.16
    0.09
    81
    +0.12
    0.08
    51
    +0.12
    0.06
    Negative Logits
    ĻĤ
    -2.52
    Ļª
    -2.03
    į
    -1.88
    ·¸
    -1.86
    omitempty
    -1.84
    ŀ
    -1.81
    Ĩ
    -1.80
    ´
    -1.77
    ĭ
    -1.76
    ĨĴ
    -1.67
    POSITIVE LOGITS
    thy
    1.44
     autres
    1.41
    phia
    1.39
    acles
    1.37
    phis
    1.36
     amongst
    1.35
    NPs
    1.35
    dt
    1.35
     gotten
    1.33
    aber
    1.30
    Activations Density 0.217%

    No Known Activations