© 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. 26901
    Prev
    Next
    INDEX
    Explanations

    phrases indicating general consensus or common occurrences

    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
    273
    +0.12
    0.7%
    194
    +0.12
    0.7%
    176
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.12
    0.06
    225
    +0.12
    0.05
    423
    +0.11
    0.05
    Negative Logits
    catch
    -1.71
     minute
    -1.44
     encounter
    -1.41
     exchanged
    -1.38
     applicable
    -1.37
     catch
    -1.36
     read
    -1.35
    atase
    -1.34
     Staff
    -1.34
     negligence
    -1.34
    POSITIVE LOGITS
    hta
    1.63
    acha
    1.61
    icago
    1.58
    smallcaps
    1.55
    rano
    1.55
    urope
    1.53
    nai
    1.53
     bras
    1.50
    ymphony
    1.47
     heels
    1.46
    Activations Density 0.396%

    No Known Activations