© 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. 2-MLP-SM
    11. 26031
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and characters

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    148
    +0.17
    1.0%
    497
    +0.12
    0.6%
    230
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.17
    0.06
    148
    +0.12
    0.06
    374
    +0.11
    0.04
    Negative Logits
     Suite
    -1.78
    ulus
    -1.71
    voir
    -1.63
    quo
    -1.58
    nen
    -1.54
    mile
    -1.47
    Newton
    -1.47
     firm
    -1.46
    Decided
    -1.45
    Sea
    -1.42
    POSITIVE LOGITS
    ĻĤ
    3.80
    Ļª
    3.22
    ¿½
    3.12
    °
    3.12
    Ĵ
    3.10
    Ĭ
    3.06
    ľĵ
    2.92
    č↵
    2.86
     ↵
    2.86
    ↵
    2.86
    Activations Density 0.471%

    No Known Activations