© 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 EvalsExportsinterp-engineNEWAPI 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. 30341
    Prev
    Next
    INDEX
    Explanations

    occurrences of JSON-like structures or objects

    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
    466
    +0.18
    1.0%
    100
    +0.17
    1.0%
    51
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.18
    0.01
    466
    +0.17
    0.01
    51
    +0.14
    0.01
    Negative Logits
    orer
    -1.79
    "}](#
    -1.78
    ](
    -1.67
    ación
    -1.66
    ]:
    -1.59
    ]));
    -1.59
    uler
    -1.58
    "}\].
    -1.54
     werden
    -1.52
    \]](
    -1.51
    POSITIVE LOGITS
    ¤
    2.01
    ¸
    1.91
    ¿½
    1.88
    ¥
    1.83
    Ķ
    1.81
    Ĺ
    1.67
     customs
    1.66
    ¡
    1.63
    Īĺ
    1.56
    chitz
    1.52
    Activations Density 0.017%

    No Known Activations