© 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. 28419
    Prev
    Next
    INDEX
    Explanations

    code-related statements and syntactical elements

    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
    115
    +0.13
    0.7%
    424
    +0.13
    0.7%
    466
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.39
    53
    +0.13
    0.42
    56
    +0.10
    0.11
    Negative Logits
    ards
    -1.72
    ping
    -1.71
    ming
    -1.68
    ability
    -1.64
    oust
    -1.56
    gon
    -1.52
    fections
    -1.48
    ding
    -1.46
     cards
    -1.45
    dy
    -1.45
    POSITIVE LOGITS
    ¶
    4.29
    ĻĤ
    4.22
    £
    4.17
    °
    4.07
      ↵
    4.06
    ↵        ↵
    4.05
    4.05
    4.05
         ↵
    4.05
    ↵
    4.05
    Activations Density 4.637%

    No Known Activations