© 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. 26406
    Prev
    Next
    INDEX
    Explanations

    terms related to specific materials and substances, particularly in the context of science and technology

    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
    276
    +0.16
    0.9%
    58
    +0.13
    0.7%
    370
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.16
    0.04
    370
    +0.13
    0.03
    111
    +0.12
    0.03
    Negative Logits
    Īĺ
    -2.42
    ģ
    -2.25
    ħ
    -2.23
    ĭ
    -2.20
    ĥ½
    -2.19
    »
    -2.12
    Ľ
    -2.09
    ¾
    -1.99
    ī
    -1.92
    Ħ
    -1.92
    POSITIVE LOGITS
    áĢ¬
    1.83
    rely
    1.80
    áĢ¯
    1.76
    ly
    1.63
    estly
    1.56
    alion
    1.55
    uka
    1.49
     pity
    1.48
    burgh
    1.48
    ening
    1.44
    Activations Density 0.076%

    No Known Activations