© 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. 29842
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Loading"

    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
    29
    +0.12
    0.7%
    361
    +0.11
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.12
    0.01
    90
    +0.11
    0.01
    29
    +0.10
    0.01
    Negative Logits
    ī
    -2.20
    ®
    -2.13
    ·¸
    -2.11
    ¿
    -2.06
    ĸ´
    -2.05
    ľ
    -2.01
    ĥ½
    -1.93
    ¯
    -1.89
    §
    -1.81
    ĨĴ
    -1.80
    POSITIVE LOGITS
    aho
    1.84
    cule
    1.84
    starter
    1.73
    ister
    1.58
     version
    1.56
     --
    1.56
    naire
    1.48
    er
    1.48
     offence
    1.46
    pone
    1.44
    Activations Density 0.010%

    No Known Activations