© 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. 0-MLP-SM
    11. 30334
    Prev
    Next
    INDEX
    Explanations

    repeated references to "our" highlighting a sense of ownership or belonging

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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%
    329
    +0.11
    0.6%
    425
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.11
    0.10
    402
    +0.11
    0.10
    114
    +0.11
    0.07
    Negative Logits
    ĨĴ
    -3.64
    Ĺ
    -3.15
    IJ
    -3.08
    ĻĤ
    -2.98
    ¸
    -2.96
    ±
    -2.95
    ¼
    -2.95
    ©
    -2.93
    Ļ
    -2.86
    Ķ
    -2.86
    POSITIVE LOGITS
    onuclear
    1.89
    tern
    1.66
     focusing
    1.63
    rogen
    1.58
     fault
    1.57
    proof
    1.56
     preserving
    1.52
    abor
    1.52
    ally
    1.52
    stit
    1.50
    Activations Density 0.101%

    No Known Activations