© 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. 25440
    Prev
    Next
    INDEX
    Explanations

    instances of permission or restrictions

    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
    269
    +0.12
    0.7%
    312
    +0.11
    0.6%
    228
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.12
    0.07
    325
    +0.11
    0.08
    104
    +0.10
    0.06
    Negative Logits
    ftime
    -1.60
     notch
    -1.59
    launchpad
    -1.42
    ()).
    -1.40
    inho
    -1.40
     beating
    -1.39
    %=
    -1.35
    robe
    -1.29
     phon
    -1.28
    venue
    -1.27
    POSITIVE LOGITS
     {#
    1.78
    **_
    1.74
    Īĺ
    1.72
    outs
    1.65
    hood
    1.61
    pers
    1.60
    :**
    1.59
     **
    1.57
    pace
    1.54
    stein
    1.51
    Activations Density 0.781%

    No Known Activations