© 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. 28483
    Prev
    Next
    INDEX
    Explanations

    references to professionals or experts in various fields

    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
    +0.18
    1.1%
    376
    +0.15
    0.9%
    173
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.18
    0.00
    156
    +0.15
    0.01
    258
    +0.11
    0.01
    Negative Logits
    ©
    -1.86
    Į
    -1.61
    woke
    -1.61
    ¿½
    -1.54
     denial
    -1.53
    Ĵ
    -1.48
     kind
    -1.44
     Acad
    -1.43
    Ĥ
    -1.41
     gay
    -1.40
    POSITIVE LOGITS
    creen
    1.88
    imus
    1.84
    imal
    1.81
    hell
    1.77
    oft
    1.74
    erals
    1.73
    ystems
    1.69
    ynaptic
    1.63
    ional
    1.62
    idian
    1.60
    Activations Density 3.572%

    No Known Activations