© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 25610
    Prev
    Next
    INDEX
    Explanations

    phrases related to research methodologies and planning

    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
    178
    +0.14
    0.8%
    407
    +0.12
    0.7%
    409
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.14
    0.15
    356
    +0.12
    0.17
    407
    +0.11
    0.18
    Negative Logits
     caution
    -1.60
    gov
    -1.49
     light
    -1.49
    ncia
    -1.45
    gel
    -1.43
    us
    -1.43
     faith
    -1.41
    VA
    -1.41
    AMA
    -1.31
    osity
    -1.30
    POSITIVE LOGITS
    ridges
    1.50
    icago
    1.47
     controls
    1.42
    ugu
    1.41
     occupies
    1.40
    disambiguation
    1.37
    webpack
    1.34
    Simplify
    1.34
    riber
    1.34
    fiddle
    1.33
    Activations Density 2.699%

    No Known Activations