© 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. 2-MLP-SM
    11. 24952
    Prev
    Next
    INDEX
    Explanations

    variations of the UTF encoding format

    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
    23
    +0.16
    0.9%
    74
    +0.13
    0.7%
    391
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.16
    0.01
    86
    +0.13
    0.01
    352
    +0.11
    0.01
    Negative Logits
    biamo
    -1.83
    stdio
    -1.74
    endl
    -1.60
    boards
    -1.60
    wegian
    -1.57
    ymphony
    -1.56
    Verlag
    -1.55
     blogs
    -1.45
    izoph
    -1.43
    aphr
    -1.42
    POSITIVE LOGITS
    soever
    1.71
    keit
    1.52
     suppose
    1.50
     ally
    1.47
    cing
    1.44
     subordinate
    1.43
     prey
    1.40
     light
    1.37
     union
    1.36
     simply
    1.34
    Activations Density 0.056%

    No Known Activations