© 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. 29948
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "riv" 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
    111
    +0.16
    0.9%
    177
    +0.14
    0.8%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    177
    +0.14
    0.01
    274
    +0.12
    0.01
    Negative Logits
    bris
    -1.53
     slightest
    -1.51
    latest
    -1.47
    cept
    -1.43
    rium
    -1.42
     gente
    -1.42
     why
    -1.40
     longest
    -1.40
     largest
    -1.39
     robust
    -1.39
    POSITIVE LOGITS
    ŀ
    2.20
    ·
    1.99
    igan
    1.97
    ĥ½
    1.92
    ģ
    1.88
    ¢
    1.84
    ¡
    1.82
    Ĭ
    1.81
    IJ
    1.80
    ¹
    1.79
    Activations Density 0.014%

    No Known Activations