© 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. 24725
    Prev
    Next
    INDEX
    Explanations

    structured data elements or code syntax

    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
    156
    +0.53
    3.9%
    111
    +0.49
    3.5%
    56
    +0.09
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.53
    0.02
    174
    +0.49
    0.02
    149
    +0.09
    0.01
    Negative Logits
    ĥ½
    -3.17
    č↵
    -3.08
    ↵
    -3.08
    ↵  ³³³
    -3.08
    -3.08
    <|outofrange|>
    -3.08
    ↵
    -3.08
    ↵↵
    -3.08
    ↵
    -3.08
    ↵↵
    -3.08
    POSITIVE LOGITS
    ses
    1.39
     offers
    1.25
     anymore
    1.19
     somewhere
    1.19
     way
    1.18
    olver
    1.15
    atured
    1.12
    anguage
    1.12
    herry
    1.11
     because
    1.11
    Activations Density 0.029%

    No Known Activations