© 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 EvalsExportsAPI 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. 28751
    Prev
    Next
    INDEX
    Explanations

    phrases related to living or life experiences

    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
    376
    +0.15
    0.8%
    29
    +0.11
    0.6%
    358
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.15
    0.01
    207
    +0.11
    0.01
    474
    +0.11
    0.01
    Negative Logits
    Ĺ
    -1.76
    ¯
    -1.75
    oles
    -1.60
    ·¸
    -1.55
    rene
    -1.53
    ++)
    -1.49
    ...](
    -1.48
    Ĥ
    -1.47
    >]
    -1.46
    )](
    -1.44
    POSITIVE LOGITS
    aby
    1.75
     Procedure
    1.69
    InstanceState
    1.66
    bridge
    1.63
    borough
    1.60
    poser
    1.54
    srep
    1.50
    stone
    1.48
    esis
    1.48
    áĢº
    1.46
    Activations Density 0.024%

    No Known Activations