© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 26916
    Prev
    Next
    INDEX
    Explanations

    references to objects being physically attached or installed

    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%
    148
    +0.16
    0.9%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.19
    0.01
    254
    +0.16
    0.01
    463
    +0.12
    0.01
    Negative Logits
     appearance
    -1.36
    ambda
    -1.28
    ows
    -1.28
    furt
    -1.26
     propensity
    -1.26
     mate
    -1.24
    ogenous
    -1.24
    ful
    -1.23
    ening
    -1.22
     Play
    -1.22
    POSITIVE LOGITS
    aurus
    1.67
    eto
    1.60
    vat
    1.58
     office
    1.56
     offense
    1.51
    illion
    1.49
    cdn
    1.43
    di
    1.42
     above
    1.39
    ogh
    1.37
    Activations Density 0.007%

    No Known Activations