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

    Neuronpedia

    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. 0-MLP-SM
    11. 27825
    Prev
    Next
    INDEX
    Explanations

    phrases related to permission or authorization

    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
    376
    +0.13
    0.7%
    260
    +0.13
    0.7%
    472
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.13
    0.03
    260
    +0.13
    0.03
    183
    +0.12
    0.03
    Negative Logits
    hey
    -1.65
    feb
    -1.64
    CSF
    -1.59
    uld
    -1.59
    hend
    -1.54
    NT
    -1.50
    MSO
    -1.50
    ftime
    -1.49
    Prefab
    -1.49
    ubert
    -1.49
    POSITIVE LOGITS
    ĻĤ
    2.62
    ħ
    2.49
    ģ
    2.33
    ī
    2.21
    ĺ
    2.20
    Ĵ
    2.19
    ĥ
    2.17
    ↵
    2.17
    ↵↵↵
    2.17
    ↵↵
    2.17
    Activations Density 0.651%

    No Known Activations