© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26085
    Prev
    Next
    INDEX
    Explanations

    instances of the word "package" in various contexts

    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
    477
    +0.12
    0.7%
    126
    +0.11
    0.6%
    69
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.12
    0.03
    214
    +0.11
    0.02
    456
    +0.11
    0.01
    Negative Logits
     jar
    -1.53
     lantern
    -1.41
     noticing
    -1.36
    ada
    -1.36
     Wiley
    -1.32
     tasting
    -1.32
    ^[@
    -1.31
    fair
    -1.29
     between
    -1.29
     supplement
    -1.28
    POSITIVE LOGITS
    ĥ½
    3.22
    Ĭ
    2.89
    ĥ
    2.65
    £
    2.57
    Īĺ
    2.50
    ľĵ
    2.50
    ĭ
    2.47
    ħ
    2.45
    ŀ
    2.42
    ¡
    2.40
    Activations Density 0.170%

    No Known Activations