© 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. 23815
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and"

    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
    50
    +0.13
    0.7%
    227
    +0.12
    0.7%
    184
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.13
    0.02
    50
    +0.12
    0.02
    92
    +0.12
    0.02
    Negative Logits
    americ
    -1.99
    ÃŃa
    -1.82
    anc
    -1.80
    û
    -1.75
    ascular
    -1.68
    iar
    -1.66
    ontal
    -1.56
    ÈĻ
    -1.55
    /$
    -1.53
    ayan
    -1.52
    POSITIVE LOGITS
    Īĺ
    2.28
    ĺ
    1.81
    °
    1.71
    ities
    1.69
    IJ
    1.64
    Ĥ
    1.63
    º
    1.57
    ĨĴ
    1.56
    İ
    1.55
    «
    1.51
    Activations Density 0.168%

    No Known Activations