© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27679
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to description and narration

    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
    +0.22
    1.2%
    156
    +0.15
    0.9%
    457
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.22
    0.02
    364
    +0.15
    0.01
    311
    +0.14
    0.01
    Negative Logits
    illard
    -1.66
    ska
    -1.63
    uten
    -1.59
    HS
    -1.58
    ori
    -1.56
    ż
    -1.54
    \]\].
    -1.51
    enue
    -1.47
    )]{}
    -1.46
    \]]{}
    -1.42
    POSITIVE LOGITS
    ably
    2.32
     how
    1.73
     error
    1.51
     deprivation
    1.45
    omerase
    1.40
     atroc
    1.38
     disorder
    1.36
     them
    1.34
    quer
    1.33
     errors
    1.33
    Activations Density 0.010%

    No Known Activations