© 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. 23987
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was" in various contexts

    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
    420
    +0.11
    0.6%
    263
    +0.11
    0.6%
    179
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.03
    274
    +0.11
    0.04
    263
    +0.10
    0.04
    Negative Logits
    Į
    -2.56
    £
    -2.47
    ĺ
    -2.46
    ĻĤ
    -2.41
    Ī
    -2.39
    ļ
    -2.23
    Ŀ
    -2.22
    ĥ½
    -2.22
    ĥ
    -2.20
    ĸ´
    -2.19
    POSITIVE LOGITS
    ÃŃc
    1.65
    oro
    1.64
    uto
    1.60
    ké
    1.59
    umi
    1.58
    encer
    1.57
    udo
    1.56
    aptop
    1.56
    dos
    1.55
    base
    1.55
    Activations Density 0.508%

    No Known Activations