© 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. 26190
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Gl'

    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
    148
    +0.14
    0.8%
    260
    +0.12
    0.7%
    429
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.14
    0.02
    359
    +0.12
    0.02
    354
    +0.12
    0.01
    Negative Logits
    ¿½
    -2.68
    Ĭ
    -2.64
    ´
    -2.49
    Ĺ
    -2.40
    ¥
    -2.38
    Ļ
    -2.25
    ĸ´
    -2.24
    ĥ
    -2.22
    ĩ
    -2.20
    ĭ
    -2.18
    POSITIVE LOGITS
    asgow
    1.77
    market
    1.58
    Rptr
    1.56
    oby
    1.45
    obe
    1.44
    bank
    1.41
    CRO
    1.37
    FW
    1.37
     Harbor
    1.35
    pen
    1.33
    Activations Density 0.871%

    No Known Activations