© 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 EvalsExportsAPI 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. 28754
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or measurements

    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
    156
    +0.21
    1.2%
    373
    +0.13
    0.8%
    308
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.21
    0.02
    308
    +0.13
    0.02
    187
    +0.11
    0.02
    Negative Logits
    aking
    -1.70
    rele
    -1.58
    aded
    -1.52
    ider
    -1.46
    verting
    -1.44
    udes
    -1.41
    tered
    -1.41
     syndrome
    -1.37
    outing
    -1.36
    icating
    -1.35
    POSITIVE LOGITS
    į
    2.68
    ĩ
    2.67
    Ĵ
    2.61
    Ķ
    2.59
    Ĭ
    2.56
    Ļ
    2.35
    ŀ
    2.34
    »
    2.25
    ļ
    2.21
    º
    2.20
    Activations Density 0.062%

    No Known Activations