© 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. 28795
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and associated terms

    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%
    382
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.19
    0.01
    273
    +0.14
    0.01
    365
    +0.13
    0.01
    Negative Logits
     covered
    -1.40
     ER
    -1.38
    sel
    -1.38
    EP
    -1.38
    mel
    -1.35
     toll
    -1.34
    tig
    -1.31
    endif
    -1.31
    exposed
    -1.30
    elves
    -1.30
    POSITIVE LOGITS
    kowski
    1.58
     Wars
    1.55
    iston
    1.53
    arser
    1.53
    ptions
    1.52
    ixel
    1.52
    icz
    1.51
    ariate
    1.41
    opard
    1.41
    ovsky
    1.40
    Activations Density 0.017%

    No Known Activations