© 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. 25956
    Prev
    Next
    INDEX
    Explanations

    information related to funding and support efforts for a research initiative, especially in the context of community engagement and partnerships

    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
    179
    +0.13
    0.7%
    485
    +0.11
    0.6%
    387
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.13
    0.15
    170
    +0.11
    0.13
    441
    +0.10
    0.09
    Negative Logits
    ité
    -1.55
    usk
    -1.46
    ```
    -1.43
    ison
    -1.41
    imes
    -1.36
    paper
    -1.34
    annel
    -1.34
    mt
    -1.34
    ipeg
    -1.33
    oll
    -1.29
    POSITIVE LOGITS
    Ī
    3.58
     ↵
    2.79
    ↵
    2.79
    2.79
    2.79
    čč
    2.79
           ↵
    2.79
    ↵
    2.79
    2.79
    ↵
    2.79
    Activations Density 3.285%

    No Known Activations