© 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. 2-MLP-SM
    11. 24135
    Prev
    Next
    INDEX
    Explanations

    XML or HTML 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
    156
    +0.21
    1.2%
    47
    +0.17
    1.0%
    354
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.21
    0.03
    149
    +0.17
    0.02
    386
    +0.13
    0.01
    Negative Logits
    Ĭ
    -3.82
    ¾
    -3.52
    ĸ´
    -3.42
    ¼
    -3.37
    ±
    -3.37
    »¿
    -3.28
    Ļª
    -3.27
    IJ
    -3.23
    ı
    -3.19
    ª
    -3.17
    POSITIVE LOGITS
    ess
    1.44
    like
    1.38
     ourselves
    1.37
    Changed
    1.36
    ]{.
    1.34
    owitz
    1.33
    constant
    1.33
     disadvantage
    1.31
    imps
    1.29
    cens
    1.29
    Activations Density 0.132%

    No Known Activations