© 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. 26109
    Prev
    Next
    INDEX
    Explanations

    expressions of ambition or desire for positive outcomes

    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
    +0.19
    1.1%
    260
    +0.11
    0.7%
    262
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.19
    0.02
    262
    +0.11
    0.02
    58
    +0.11
    0.02
    Negative Logits
    minded
    -1.88
    erated
    -1.80
    ITED
    -1.72
    vist
    -1.66
     degree
    -1.66
     herself
    -1.63
     privileges
    -1.56
    >(
    -1.53
    eration
    -1.52
    azar
    -1.46
    POSITIVE LOGITS
    bourg
    1.48
    iol
    1.42
    old
    1.40
     opera
    1.39
    manship
    1.38
    semble
    1.36
    not
    1.36
     precedent
    1.34
    burg
    1.34
    onies
    1.34
    Activations Density 0.051%

    No Known Activations