© 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. 25060
    Prev
    Next
    INDEX
    Explanations

    components related to community and social interactions

    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
    9
    +0.17
    1.0%
    0
    +0.11
    0.6%
    455
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.17
    0.07
    0
    +0.11
    0.07
    511
    +0.11
    0.02
    Negative Logits
     panel
    -1.50
    Panel
    -1.47
     apologize
    -1.43
     candidate
    -1.42
     estimation
    -1.40
     appearance
    -1.40
     expected
    -1.38
     estimated
    -1.36
    ĨĴ
    -1.34
     analysts
    -1.33
    POSITIVE LOGITS
    enses
    1.52
    lets
    1.51
     nets
    1.51
    uscular
    1.50
    ovir
    1.47
    compat
    1.41
    itas
    1.40
    yrinth
    1.37
    lessly
    1.37
    io
    1.36
    Activations Density 1.771%

    No Known Activations