© 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. 2-MLP-SM
    11. 23689
    Prev
    Next
    INDEX
    Explanations

    mentions of selection rounds and drafts, particularly in competition 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.16
    0.9%
    192
    +0.15
    0.8%
    349
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.16
    0.03
    192
    +0.15
    0.01
    23
    +0.13
    0.01
    Negative Logits
    roup
    -1.58
     chron
    -1.56
     generality
    -1.53
     notation
    -1.49
    er
    -1.49
     household
    -1.49
     innings
    -1.49
     yourself
    -1.46
     emotionally
    -1.44
     boundaries
    -1.43
    POSITIVE LOGITS
    µ
    2.56
    ¯
    2.31
    Į
    2.31
    ·
    2.27
    ¸
    2.17
    ¿½
    2.13
    ´
    2.11
    Ģ
    2.11
    ·¸
    2.06
    ĸ´
    2.05
    Activations Density 0.411%

    No Known Activations