© 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. 27166
    Prev
    Next
    INDEX
    Explanations

    references to specific technical identifiers or programming-related terms

    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
    81
    +0.13
    0.7%
    230
    +0.13
    0.7%
    130
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.13
    0.04
    388
    +0.13
    0.04
    187
    +0.13
    0.04
    Negative Logits
    iencies
    -1.67
     answer
    -1.64
    acious
    -1.64
    Ļª
    -1.59
    arers
    -1.57
    king
    -1.56
    Īĺ
    -1.56
    ¿
    -1.55
    arer
    -1.51
     others
    -1.51
    POSITIVE LOGITS
    BOX
    1.85
    igen
    1.79
    eno
    1.77
    AML
    1.77
    enos
    1.77
    iga
    1.76
    edo
    1.74
    pert
    1.66
    FC
    1.65
    plic
    1.64
    Activations Density 0.260%

    No Known Activations