© 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 EvalsExportsAPI 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. 28543
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "for"

    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
    495
    +0.13
    0.7%
    400
    +0.12
    0.7%
    325
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.28
    98
    +0.12
    0.11
    173
    +0.12
    0.20
    Negative Logits
     contrary
    -1.60
     ceiling
    -1.46
     upside
    -1.45
     Square
    -1.42
    itely
    -1.41
    UTERS
    -1.37
     theft
    -1.36
    icon
    -1.32
    astern
    -1.30
    iels
    -1.30
    POSITIVE LOGITS
    Ĥ¬
    3.13
    ij
    3.11
    į
    3.02
    Ī
    2.91
    »
    2.83
    ¤
    2.77
    Ļ
    2.73
    Ĥ
    2.73
    ľ
    2.70
    ĻĤ
    2.65
    Activations Density 1.576%

    No Known Activations