© 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. 23236
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that suggest reasoning or cause-and-effect relationships

    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
    154
    +0.12
    0.7%
    507
    +0.11
    0.6%
    337
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.12
    0.01
    356
    +0.11
    0.01
    468
    +0.11
    0.00
    Negative Logits
    imus
    -2.04
    iously
    -1.72
     critics
    -1.55
    ché
    -1.51
    antis
    -1.51
    Americans
    -1.48
     refrain
    -1.46
    writers
    -1.44
    andum
    -1.43
    atives
    -1.39
    POSITIVE LOGITS
    Īĺ
    1.97
    ĻĤ
    1.82
    ķ
    1.82
    ¬
    1.76
    ı
    1.74
    ļ
    1.63
    ģ
    1.62
    ¨
    1.62
    hin
    1.61
    ¤
    1.60
    Activations Density 0.001%

    No Known Activations