© 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. 26056
    Prev
    Next
    INDEX
    Explanations

    text related to regulations or policies

    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
    241
    +0.11
    0.6%
    410
    +0.11
    0.6%
    76
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.11
    0.01
    264
    +0.11
    0.01
    214
    +0.11
    0.01
    Negative Logits
    )$)
    -1.67
    ôle
    -1.50
    aten
    -1.49
    ITLE
    -1.46
    assis
    -1.45
    accord
    -1.44
    OURCE
    -1.43
    abbit
    -1.42
    ijer
    -1.40
    ../../
    -1.40
    POSITIVE LOGITS
    ĻĤ
    2.36
    §
    2.32
    Ļª
    2.12
    ĩ
    1.92
    «
    1.82
    Ľ
    1.82
    Ŀ
    1.79
    ģ
    1.77
    Ī
    1.71
    ¯
    1.68
    Activations Density 0.010%

    No Known Activations