© 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 EvalsExportsAPI 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. 28348
    Prev
    Next
    INDEX
    Explanations

    sequences of values or expressions associated with mathematical or programming functions

    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
    318
    +0.14
    0.8%
    12
    +0.13
    0.7%
    106
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.22
    486
    +0.13
    0.15
    154
    +0.13
    0.14
    Negative Logits
    ↵Č
    -4.36
    <|outofrange|>
    -4.36
       ↵
    -4.36
    ↵
    -4.36
    -4.36
    <|outofrange|>
    -4.36
    ↵↵
    -4.36
    č↵č↵
    -4.36
         ↵
    -4.36
    ↵↵
    -4.36
    POSITIVE LOGITS
    pez
    1.82
    girl
    1.63
    antine
    1.58
    okrat
    1.51
    otropic
    1.49
     postpartum
    1.44
    vester
    1.44
     diet
    1.43
     breast
    1.42
    uable
    1.42
    Activations Density 0.401%

    No Known Activations