© 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. 26379
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "investigated" in various contexts

    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
    +0.21
    1.2%
    156
    +0.20
    1.1%
    115
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.21
    0.01
    393
    +0.20
    0.01
    293
    +0.13
    0.01
    Negative Logits
     represented
    -1.61
    itsu
    -1.56
     dominated
    -1.55
    ened
    -1.51
     celebrated
    -1.48
     reductase
    -1.48
    chts
    -1.47
     assessed
    -1.46
    elijk
    -1.36
     propensity
    -1.36
    POSITIVE LOGITS
    ĻĤ
    1.54
    ¤
    1.49
    geries
    1.46
    ifle
    1.46
    itudes
    1.45
    ¿½
    1.43
     beforehand
    1.42
    gender
    1.41
    uments
    1.40
    ités
    1.39
    Activations Density 0.007%

    No Known Activations