© 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. 26676
    Prev
    Next
    INDEX
    Explanations

    technical terms related to sound or audio

    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
    +0.13
    0.7%
    77
    +0.13
    0.7%
    227
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.13
    0.01
    227
    +0.13
    0.01
    462
    +0.13
    0.01
    Negative Logits
     ");
    -1.51
     affairs
    -1.48
    ");
    -1.44
     Association
    -1.44
    comm
    -1.43
    )\].
    -1.42
    /-/
    -1.41
    /">
    -1.40
     LICENSE
    -1.40
    )}.$$
    -1.39
    POSITIVE LOGITS
    thouse
    1.81
    ibase
    1.57
    osph
    1.53
    ingly
    1.53
    ró
    1.52
    endar
    1.50
     witness
    1.48
    osome
    1.43
    ât
    1.42
    lace
    1.40
    Activations Density 0.484%

    No Known Activations