© 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. 26587
    Prev
    Next
    INDEX
    Explanations

    references to the FBI and related organizations or figures

    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
    156
    +0.26
    1.5%
    71
    +0.12
    0.7%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.26
    0.02
    156
    +0.12
    0.01
    412
    +0.12
    0.01
    Negative Logits
     gay
    -1.63
    woke
    -1.56
     hyperb
    -1.47
    qq
    -1.44
    hes
    -1.43
    ayed
    -1.38
    opus
    -1.38
     queer
    -1.37
    ){#
    -1.37
    tetra
    -1.35
    POSITIVE LOGITS
    »¿
    2.37
    ²
    2.10
    Ľ
    2.02
    ĩ
    1.87
    ĸ
    1.80
    ļ
    1.80
    iplinary
    1.74
    ª
    1.74
    ®
    1.73
    ģ
    1.71
    Activations Density 0.035%

    No Known Activations