© 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. 25412
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shifted" or related variations indicating change or movement

    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
    376
    +0.21
    1.2%
    156
    +0.20
    1.2%
    142
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.21
    0.01
    89
    +0.20
    0.01
    153
    +0.11
    0.01
    Negative Logits
    ks
    -1.71
    aves
    -1.54
    hops
    -1.54
    _"
    -1.47
    lessly
    -1.40
     refreshing
    -1.38
    neys
    -1.36
    eners
    -1.35
    itsu
    -1.35
     jog
    -1.35
    POSITIVE LOGITS
    ollar
    1.45
    pute
    1.40
     Legislative
    1.38
    ↵³³
    1.37
    iate
    1.35
    ĻĤ
    1.34
     extinct
    1.34
     Parenthood
    1.31
    upt
    1.28
    [\#
    1.27
    Activations Density 0.030%

    No Known Activations