© 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. 25496
    Prev
    Next
    INDEX
    Explanations

    instances of the word "focus" and its variations in context

    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
    321
    +0.13
    0.7%
    242
    +0.11
    0.6%
    145
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.13
    0.03
    321
    +0.11
    0.03
    67
    +0.10
    0.03
    Negative Logits
    ĵ
    -2.01
    )?
    -1.70
    ”.
    -1.66
    ”).
    -1.61
    )!
    -1.61
    Ľ
    -1.58
    adesh
    -1.58
    IJ
    -1.58
    pgen
    -1.52
    úblic
    -1.51
    POSITIVE LOGITS
    etus
    1.53
     credibility
    1.49
     goose
    1.47
     credit
    1.41
    cale
    1.38
     Bart
    1.38
     bureau
    1.34
     friend
    1.33
    chaft
    1.33
     bet
    1.32
    Activations Density 0.304%

    No Known Activations