© 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. 23983
    Prev
    Next
    INDEX
    Explanations

    references to events, storylines, or social phenomena

    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
    +0.13
    0.7%
    212
    +0.13
    0.7%
    143
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.13
    0.00
    380
    +0.13
    0.01
    347
    +0.12
    0.01
    Negative Logits
    Į
    -1.91
    ĥ½
    -1.72
    ļ
    -1.68
    ischen
    -1.61
     explor
    -1.54
    istry
    -1.53
     forums
    -1.52
    forum
    -1.49
    obiles
    -1.45
     nov
    -1.45
    POSITIVE LOGITS
    pered
    1.67
     Stafford
    1.62
    over
    1.51
     Pence
    1.49
     terminated
    1.46
    cov
    1.37
    dorff
    1.35
     heir
    1.34
    seen
    1.34
     graft
    1.30
    Activations Density 0.049%

    No Known Activations