© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26731
    Prev
    Next
    INDEX
    Explanations

    mentions of specific identity groups and related political dynamics

    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
    156
    +0.29
    1.7%
    27
    +0.13
    0.8%
    47
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.29
    0.14
    353
    +0.13
    0.14
    140
    +0.13
    0.08
    Negative Logits
     exceptions
    -1.57
    ık
    -1.48
    blogger
    -1.48
     occurs
    -1.47
    ĥ½
    -1.45
    £
    -1.45
    <|outofrange|>
    -1.43
    -1.43
    ↵
    -1.43
    ↵
    -1.43
    POSITIVE LOGITS
    ```
    1.46
     pier
    1.31
    svg
    1.30
     override
    1.28
    registry
    1.27
    psy
    1.26
    ?.
    1.25
     envy
    1.24
     uncontrolled
    1.22
     \-
    1.22
    Activations Density 2.938%

    No Known Activations