© 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. 23001
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and syntax elements

    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
    +0.29
    1.7%
    344
    +0.11
    0.6%
    36
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.29
    0.12
    23
    +0.11
    0.05
    354
    +0.10
    0.08
    Negative Logits
    ÃŃf
    -2.28
    heets
    -1.81
    heet
    -1.72
    pora
    -1.64
     caption
    -1.63
     via
    -1.46
    paces
    -1.42
    ific
    -1.41
    ÃŃa
    -1.41
     calculation
    -1.40
    POSITIVE LOGITS
    Ļª
    1.71
    áĢ¯
    1.58
    Hop
    1.45
    atten
    1.44
    oscopic
    1.43
    odor
    1.42
    ureth
    1.41
    acid
    1.41
    amine
    1.40
    uniform
    1.36
    Activations Density 1.705%

    No Known Activations