© 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. 29214
    Prev
    Next
    INDEX
    Explanations

    terms related to conspiracies

    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
    +0.17
    1.0%
    314
    +0.12
    0.7%
    228
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.01
    314
    +0.12
    0.01
    264
    +0.10
    0.01
    Negative Logits
    iki
    -1.71
    izi
    -1.49
    MOESM
    -1.46
     âĻª"
    -1.43
    dered
    -1.41
     someday
    -1.39
     Dad
    -1.38
     dear
    -1.37
     precious
    -1.37
    ____________
    -1.36
    POSITIVE LOGITS
     theory
    2.01
     theories
    1.70
     theor
    1.65
    umes
    1.52
    theory
    1.52
    esium
    1.49
    oon
    1.47
     counts
    1.47
     variables
    1.44
     scenario
    1.43
    Activations Density 0.031%

    No Known Activations