© 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. 30412
    Prev
    Next
    INDEX
    Explanations

    instances of the word "letter" in various contexts

    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
    +0.19
    1.1%
    360
    +0.13
    0.7%
    249
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.19
    0.03
    133
    +0.13
    0.02
    174
    +0.11
    0.02
    Negative Logits
    ĥ½
    -4.42
    ķ
    -4.01
    ¬
    -4.00
    ½
    -3.82
    ¸
    -3.75
    Ŀ
    -3.66
    IJ
    -3.62
    ¿
    -3.58
    ¹
    -3.58
    ħ
    -3.58
    POSITIVE LOGITS
    head
    2.05
    heads
    1.95
    ahead
    1.88
    room
    1.79
    making
    1.77
     opener
    1.69
    posts
    1.68
    mong
    1.66
    matter
    1.66
    worm
    1.63
    Activations Density 0.016%

    No Known Activations