© 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. 25480
    Prev
    Next
    INDEX
    Explanations

    terms related to semantic analysis and its applications

    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%
    266
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.21
    0.01
    156
    +0.12
    0.01
    219
    +0.12
    0.01
    Negative Logits
    ureus
    -1.64
     kisses
    -1.50
    ½
    -1.49
     Jr
    -1.48
     ÏĮÏĦι
    -1.44
     them
    -1.44
    ahren
    -1.43
     awake
    -1.41
     eggs
    -1.41
     Promise
    -1.40
    POSITIVE LOGITS
    fiddle
    2.02
    herry
    1.65
    wise
    1.61
    itet
    1.59
     mattered
    1.56
    processing
    1.51
    "}](#
    1.50
    cell
    1.49
    committee
    1.47
    cial
    1.47
    Activations Density 0.462%

    No Known Activations