© 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. 0-MLP-SM
    11. 26783
    Prev
    Next
    INDEX
    Explanations

    the possessive pronoun "his"

    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
    428
    +0.13
    0.7%
    132
    +0.13
    0.7%
    462
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    96
    +0.13
    0.11
    120
    +0.13
    0.09
    191
    +0.12
    0.09
    Negative Logits
    bital
    -1.65
    tion
    -1.61
    vier
    -1.55
    ENCE
    -1.51
    acion
    -1.50
    ATION
    -1.44
    cardia
    -1.44
    fight
    -1.44
    ech
    -1.42
    OUS
    -1.41
    POSITIVE LOGITS
     behalf
    1.81
    cks
    1.64
    cases
    1.59
     midst
    1.46
     various
    1.46
    heres
    1.41
    gow
    1.40
    com
    1.37
    ails
    1.35
    innati
    1.33
    Activations Density 0.143%

    No Known Activations