© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22651
    Prev
    Next
    INDEX
    Explanations

    phrases that signify direction or path

    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
    375
    +0.12
    0.6%
    452
    +0.11
    0.6%
    163
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.12
    0.02
    275
    +0.11
    0.01
    452
    +0.10
    0.02
    Negative Logits
    dfrac
    -1.57
    terior
    -1.48
    ighter
    -1.45
    usepackage
    -1.42
    ?",
    -1.41
     decir
    -1.39
    oretical
    -1.37
    thereum
    -1.37
    atu
    -1.37
     Asia
    -1.36
    POSITIVE LOGITS
    âĢĬ
    1.52
     µm
    1.35
    .<
    1.35
     []
    1.34
     Âĵ
    1.34
     MCL
    1.32
     Apr
    1.30
     graduated
    1.30
     grav
    1.28
     eds
    1.27
    Activations Density 0.247%

    No Known Activations