© 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. 30152
    Prev
    Next
    INDEX
    Explanations

    references to teams and their membership

    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
    +0.13
    0.8%
    444
    +0.13
    0.7%
    119
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.13
    0.03
    429
    +0.13
    0.03
    385
    +0.13
    0.02
    Negative Logits
    ·¸
    -1.51
    ĺ
    -1.46
     remembering
    -1.40
    ores
    -1.40
     myself
    -1.39
     lasted
    -1.38
    ¦
    -1.37
    ytes
    -1.37
     tears
    -1.36
     buried
    -1.34
    POSITIVE LOGITS
    ings
    1.92
    jen
    1.56
    ague
    1.53
    ibilit
    1.53
    scala
    1.47
    ibles
    1.45
    vers
    1.44
    ers
    1.44
    boro
    1.44
    aways
    1.43
    Activations Density 0.119%

    No Known Activations