© 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. 24128
    Prev
    Next
    INDEX
    Explanations

    possessive forms of words, particularly using "'s"

    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
    474
    +0.14
    0.8%
    391
    +0.11
    0.6%
    149
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.14
    0.06
    322
    +0.11
    0.04
    461
    +0.11
    0.06
    Negative Logits
    JECT
    -1.75
    ureus
    -1.51
    PLICATION
    -1.50
    fficients
    -1.45
    "."
    -1.38
    "_
    -1.37
    's
    -1.37
    _"
    -1.34
    Po
    -1.33
    inx
    -1.31
    POSITIVE LOGITS
    Ļ
    2.50
    ĥ½
    2.40
    ĻĤ
    2.39
    Ķ
    2.32
    ĨĴ
    2.21
    ģ
    2.17
    ·¸
    2.16
    ŀ
    2.10
    ĸ
    2.09
    ĺ
    2.08
    Activations Density 0.219%

    No Known Activations