© 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. 26664
    Prev
    Next
    INDEX
    Explanations

    elements related to music and performance

    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
    201
    +0.12
    0.6%
    88
    +0.12
    0.6%
    328
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.12
    0.08
    149
    +0.12
    0.04
    329
    +0.11
    0.01
    Negative Logits
    '):
    -1.61
    aliana
    -1.54
    )...
    -1.52
    .),
    -1.50
    .);
    -1.48
    ospel
    -1.46
    ]:
    -1.44
    ason
    -1.40
    )**
    -1.39
    ),
    -1.37
    POSITIVE LOGITS
    °
    1.65
    attention
    1.63
    »
    1.61
    ĺ
    1.59
    ¡
    1.54
    specified
    1.53
    tons
    1.51
    ·
    1.47
    Ñıв
    1.44
    eras
    1.40
    Activations Density 3.687%

    No Known Activations