© 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. 0-MLP-SM
    11. 29749
    Prev
    Next
    INDEX
    Explanations

    references to blogs and blogging activities

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    156
    +0.31
    1.9%
    87
    +0.12
    0.8%
    330
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.31
    0.01
    229
    +0.12
    0.01
    294
    +0.11
    0.01
    Negative Logits
    ©
    -2.54
    §
    -2.33
    ĥ½
    -2.21
    Ħ
    -2.13
    Į
    -2.11
    ı
    -2.09
    ·
    -2.07
    ĺ
    -2.03
    ®
    -1.99
    ĵ
    -1.94
    POSITIVE LOGITS
    pace
    1.92
    helf
    1.88
    keeping
    1.80
    erve
    1.75
    lot
    1.75
    keepers
    1.63
    matter
    1.59
    ahead
    1.59
    oon
    1.58
    igraphy
    1.52
    Activations Density 0.020%

    No Known Activations