© 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. 24198
    Prev
    Next
    INDEX
    Explanations

    words related to options and choices available

    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
    382
    +0.12
    0.7%
    117
    +0.12
    0.7%
    389
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.12
    0.03
    249
    +0.12
    0.03
    415
    +0.12
    0.01
    Negative Logits
    msgstr
    -1.74
    âĢ¦]
    -1.64
    semble
    -1.55
     reads
    -1.51
    lication
    -1.41
    dtd
    -1.39
     polls
    -1.36
    throws
    -1.34
     Should
    -1.34
    noreply
    -1.34
    POSITIVE LOGITS
    º
    3.20
    »
    3.12
    ĸ´
    3.09
    ĭ
    3.07
    Į
    2.97
    Ł
    2.91
    ´
    2.86
    Ĩ
    2.85
    ·¸
    2.85
    ↵
    2.84
    Activations Density 0.288%

    No Known Activations