© 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. 2-MLP-SM
    11. 24022
    Prev
    Next
    INDEX
    Explanations

    references to electrical current and related concepts

    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
    373
    +0.12
    0.6%
    153
    +0.11
    0.6%
    175
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.12
    0.02
    82
    +0.11
    0.01
    78
    +0.11
    0.01
    Negative Logits
    iners
    -1.69
     ’
    -1.61
     matter
    -1.52
     ‘
    -1.51
     disease
    -1.49
     office
    -1.47
    inho
    -1.47
     depends
    -1.45
    ission
    -1.44
    )\]
    -1.42
    POSITIVE LOGITS
    à¯ģ
    1.68
     HashMap
    1.65
    ி
    1.48
    à±ģ
    1.47
    akra
    1.46
    --"
    1.45
    àµį
    1.41
    áĥIJáĥ
    1.40
    lov
    1.38
    à¯į
    1.37
    Activations Density 0.167%

    No Known Activations