© 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. 26584
    Prev
    Next
    INDEX
    Explanations

    information related to files, directories, and programming functions

    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
    23
    +0.41
    2.4%
    271
    +0.15
    0.9%
    52
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.41
    0.15
    56
    +0.15
    0.17
    232
    +0.12
    0.14
    Negative Logits
    forge
    -1.92
     quo
    -1.89
    #.
    -1.83
    ów
    -1.79
    ÃŃs
    -1.78
    amiento
    -1.72
    ÃŃa
    -1.71
    ressor
    -1.70
     Stats
    -1.70
    ÃŃf
    -1.68
    POSITIVE LOGITS
     welcome
    2.28
    ľ
    1.84
    Ļª
    1.82
    ľĵ
    1.80
    ·
    1.68
    ĻĤ
    1.67
     finally
    1.64
    ŀ
    1.63
    ł
    1.63
    ·¸
    1.62
    Activations Density 2.054%

    No Known Activations