© 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. 25750
    Prev
    Next
    INDEX
    Explanations

    terms relating to peripheral regions or aspects

    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
    2
    +0.13
    0.7%
    367
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.13
    0.02
    367
    +0.12
    0.00
    299
    +0.12
    0.01
    Negative Logits
    ugu
    -1.66
    itness
    -1.60
    operated
    -1.55
    ovir
    -1.52
    ÃŃ
    -1.50
    oblastoma
    -1.48
    ukin
    -1.47
    rosophila
    -1.46
    iratory
    -1.45
    áv
    -1.43
    POSITIVE LOGITS
     reck
    1.55
     cracking
    1.49
    DECL
    1.39
     heck
    1.39
    Enum
    1.37
     theirs
    1.35
    iser
    1.35
     them
    1.35
    rift
    1.31
     minerals
    1.31
    Activations Density 0.096%

    No Known Activations