© 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. 27751
    Prev
    Next
    INDEX
    Explanations

    mentions of Samsung

    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
    156
    +0.26
    1.5%
    369
    +0.14
    0.8%
    173
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.26
    0.02
    382
    +0.14
    0.02
    271
    +0.13
    0.01
    Negative Logits
    woke
    -1.55
    ĥ½
    -1.53
     yours
    -1.49
     childhood
    -1.49
     fatal
    -1.44
     kay
    -1.38
     your
    -1.37
     mid
    -1.36
     scrolling
    -1.35
    ayed
    -1.33
    POSITIVE LOGITS
    abad
    1.93
    chen
    1.75
    erals
    1.69
    fors
    1.58
    elines
    1.58
     Electronics
    1.57
    lectual
    1.56
    itol
    1.56
    ings
    1.53
    itic
    1.52
    Activations Density 0.022%

    No Known Activations