© 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. 0-MLP-SM
    11. 29435
    Prev
    Next
    INDEX
    Explanations

    code-related terms and references to computer science components

    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
    111
    +0.16
    0.9%
    369
    +0.13
    0.7%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    320
    +0.13
    0.01
    341
    +0.12
    0.01
    Negative Logits
    Ļª
    -2.65
    ĥ
    -2.60
    »¿
    -2.46
    ĨĴ
    -2.32
    ı
    -2.29
    ¼
    -2.28
    į
    -2.27
    ·¸
    -2.25
    Ĥ¬
    -2.24
    ¿
    -2.14
    POSITIVE LOGITS
    rill
    1.71
    lic
    1.70
    bers
    1.58
    rant
    1.57
    otrophic
    1.56
    igent
    1.51
    enos
    1.46
     awarded
    1.46
    greg
    1.45
    [,
    1.44
    Activations Density 0.060%

    No Known Activations