© 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. 2-MLP-SM
    11. 22765
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "of" in various contexts, indicating its significance in the text

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.15
    0.8%
    363
    +0.11
    0.6%
    349
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.15
    0.05
    349
    +0.11
    0.05
    119
    +0.11
    0.03
    Negative Logits
     background
    -1.72
     remainder
    -1.70
    enium
    -1.54
     drawn
    -1.48
     {#
    -1.44
    fiddle
    -1.42
    of
    -1.41
     heap
    -1.40
    ajan
    -1.39
    ringe
    -1.36
    POSITIVE LOGITS
    ĥ½
    2.66
    ¿½
    2.37
    Ĺ
    2.13
    ľĵ
    2.12
    ²
    2.07
    Ĭ
    2.06
    ł
    2.06
    Ł
    2.03
    µ
    2.01
    Īĺ
    1.97
    Activations Density 0.306%

    No Known Activations