© 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. 26900
    Prev
    Next
    INDEX
    Explanations

    references to darkness and its associated themes

    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
    156
    +0.19
    1.0%
    191
    +0.11
    0.6%
    118
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.19
    0.01
    180
    +0.11
    0.04
    218
    +0.10
    0.03
    Negative Logits
    assed
    -1.49
     FIG
    -1.45
    needed
    -1.43
    existent
    -1.43
    bbing
    -1.39
     misunderstanding
    -1.39
     goodbye
    -1.35
    mania
    -1.33
    {})
    -1.29
    igma
    -1.28
    POSITIVE LOGITS
    ers
    1.61
    acs
    1.52
    ership
    1.50
    ech
    1.49
    ita
    1.48
     Architect
    1.46
    itus
    1.46
    abin
    1.41
    orian
    1.39
    ķ
    1.39
    Activations Density 0.762%

    No Known Activations