© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-MLP-SM
    11. 25652
    Prev
    Next
    INDEX
    Explanations

    words related to music and artists

    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
    492
    +0.13
    0.7%
    18
    +0.12
    0.7%
    89
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.13
    0.02
    23
    +0.12
    0.02
    38
    +0.11
    0.01
    Negative Logits
    efs
    -1.63
     depend
    -1.54
     favour
    -1.52
    onical
    -1.52
    esters
    -1.46
     favor
    -1.45
    ibi
    -1.43
     shells
    -1.42
     —
    -1.42
     dominates
    -1.41
    POSITIVE LOGITS
    ª
    3.00
    ķ
    2.82
    Ĺ
    2.78
    ¿½
    2.67
    »
    2.67
    ¡
    2.58
    ±
    2.55
    ĨĴ
    2.53
    ¥
    2.52
    ²
    2.49
    Activations Density 0.409%

    No Known Activations