© 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. 23171
    Prev
    Next
    INDEX
    Explanations

    references to time and duration

    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
    455
    +0.12
    0.7%
    277
    +0.12
    0.6%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.12
    0.06
    403
    +0.12
    0.04
    455
    +0.11
    0.05
    Negative Logits
    ľ
    -1.82
    į
    -1.59
    Ķ
    -1.56
    lder
    -1.51
    ĺ
    -1.50
    »¿
    -1.46
    ķ
    -1.45
    Ĥ¬
    -1.45
    ously
    -1.45
    ģ
    -1.41
    POSITIVE LOGITS
    opyright
    1.46
     preceded
    1.44
    texttt
    1.38
    Ns
    1.38
    enium
    1.35
    seys
    1.34
     anos
    1.34
    à¬
    1.33
    ioni
    1.28
     encoding
    1.26
    Activations Density 1.051%

    No Known Activations