© 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. 2-MLP-SM
    11. 27058
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

    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
    57
    +0.14
    0.8%
    45
    +0.13
    0.7%
    106
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.14
    0.04
    57
    +0.13
    0.04
    45
    +0.12
    0.05
    Negative Logits
    orescence
    -1.64
    TRODUCTION
    -1.58
    ameter
    -1.57
    amycin
    -1.55
    amid
    -1.53
    $=
    -1.50
    []{
    -1.48
    ameters
    -1.47
    racted
    -1.45
    reon
    -1.44
    POSITIVE LOGITS
    »¿
    4.07
    Ļª
    3.59
    Ĭ
    3.46
    ĩ
    3.44
    ģ
    3.42
    IJ
    3.39
    ·¸
    3.36
    ľĵ
    3.20
    ĵ
    3.17
    ĻĤ
    3.16
    Activations Density 0.196%

    No Known Activations