© 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. 25556
    Prev
    Next
    INDEX
    Explanations

    Occurrences of the word "in" and related prepositions

    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
    170
    +0.14
    0.8%
    237
    +0.12
    0.7%
    387
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.14
    0.06
    362
    +0.12
    0.05
    404
    +0.11
    0.06
    Negative Logits
     broadly
    -1.63
    atively
    -1.58
    ationally
    -1.58
    ker
    -1.55
     perturbed
    -1.48
    ,''
    -1.48
     ''
    -1.46
    ounding
    -1.44
    wide
    -1.44
    terday
    -1.41
    POSITIVE LOGITS
    »¿
    2.38
     ↵
    2.32
    č↵
    2.32
     ↵
    2.32
    ↵
    2.32
    ↵
    2.32
    2.32
    2.32
    2.32
    <|outofrange|>
    2.32
    Activations Density 0.301%

    No Known Activations