© 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. 26740
    Prev
    Next
    INDEX
    Explanations

    expressions of interest or engagement

    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
    161
    +0.10
    0.6%
    248
    +0.10
    0.6%
    41
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.10
    0.04
    163
    +0.10
    0.02
    104
    +0.10
    0.04
    Negative Logits
    ĻĤ
    -2.53
    »¿
    -2.22
    ĸ
    -2.00
    ľĵ
    -1.90
    à±į
    -1.86
    erce
    -1.84
    ?!
    -1.82
    Īĺ
    -1.78
    Ĩ
    -1.76
    ĨĴ
    -1.71
    POSITIVE LOGITS
     analyt
    1.80
     glyc
    1.59
    ]{.
    1.52
     substant
    1.48
     pore
    1.47
     prospectively
    1.43
     followed
    1.43
     metabolites
    1.42
     retrospectively
    1.42
     critically
    1.39
    Activations Density 0.496%

    No Known Activations