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

    Neuronpedia

    Jacobian LensNEW
    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. 25095
    Prev
    Next
    INDEX
    Explanations

    references to political positions or titles, particularly related to prime ministers and their actions

    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
    +0.12
    0.7%
    181
    +0.11
    0.6%
    360
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.04
    360
    +0.11
    0.01
    450
    +0.11
    0.07
    Negative Logits
    »¿
    -1.99
    Ļª
    -1.89
    pocket
    -1.61
    Ģ
    -1.54
    Ī
    -1.53
    Ĩ
    -1.44
    č↵
    -1.43
    <|outofrange|>
    -1.43
     ↵
    -1.43
    <|outofrange|>
    -1.43
    POSITIVE LOGITS
    rfloor
    1.91
    urred
    1.72
    obbsee
    1.56
    orems
    1.54
    ]"
    1.53
    aten
    1.52
    omitempty
    1.49
    solete
    1.47
    />
    1.45
    over
    1.43
    Activations Density 1.528%

    No Known Activations