© 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. 23436
    Prev
    Next
    INDEX
    Explanations

    references to organizations and government entities

    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
    175
    +0.14
    0.8%
    254
    +0.13
    0.7%
    5
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.14
    0.09
    5
    +0.13
    0.02
    255
    +0.11
    0.10
    Negative Logits
     normally
    -1.52
    dling
    -1.39
     turnover
    -1.36
     rate
    -1.35
     interchange
    -1.34
     downs
    -1.32
     injuries
    -1.31
     ramp
    -1.31
     ([@
    -1.30
    hest
    -1.30
    POSITIVE LOGITS
    ĥ½
    2.95
    ĨĴ
    2.63
    Ĵ
    2.54
    Ĩ
    2.36
    Ľ
    2.29
    ¢
    2.25
    ĭ
    2.23
    ĵ
    2.16
    ±
    2.13
    º
    2.08
    Activations Density 3.042%

    No Known Activations